[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CYSYAJEXHW1MBBQRR4WAT0":3,"skill-same:01M6CYSYAJEXHW1MBBQRR4WAT0":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":28,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6CYSYAJEXHW1MBBQRR4WAT0","owasp-security",null,"Use when reviewing code for security vulnerabilities, implementing authentication\u002Fauthorization, handling user input, or discussing web application security. Covers OWASP Top 10:2025, ASVS 5.0, and Agentic AI security (2026).","eric861129\u002FSKILLS_All-in-one","eric861129","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74950944?v=4","01M6CXHDYEYRPFGGV4EFXCSYCF","ChiYu-Huang","01M6CXHE2J5CN1EBTY0FKV3ZKW",52,"MIT","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FSecurity & Web Testing\u002Fowasp-security\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"security","owasp security","owasp","ai security","agentic","agentic ai","application security","vulnerabilities","web","owasp top 10","code","authentication","authorization","user","use","application","2026-11-10 10:12:30",false,"---\nname: owasp-security\ndescription: Use when reviewing code for security vulnerabilities, implementing authentication\u002Fauthorization, handling user input, or discussing web application security. Covers OWASP Top 10:2025, ASVS 5.0, and Agentic AI security (2026).\n---\n\n# OWASP Security Best Practices Skill\n\nApply these security standards when writing or reviewing code.\n\n## Quick Reference: OWASP Top 10:2025\n\n| # | Vulnerability | Key Prevention |\n|---|---------------|----------------|\n| A01 | Broken Access Control | Deny by default, enforce server-side, verify ownership |\n| A02 | Security Misconfiguration | Harden configs, disable defaults, minimize features |\n| A03 | Supply Chain Failures | Lock versions, verify integrity, audit dependencies |\n| A04 | Cryptographic Failures | TLS 1.2+, AES-256-GCM, Argon2\u002Fbcrypt for passwords |\n| A05 | Injection | Parameterized queries, input validation, safe APIs |\n| A06 | Insecure Design | Threat model, rate limit, design security controls |\n| A07 | Auth Failures | MFA, check breached passwords, secure sessions |\n| A08 | Integrity Failures | Sign packages, SRI for CDN, safe serialization |\n| A09 | Logging Failures | Log security events, structured format, alerting |\n| A10 | Exception Handling | Fail-closed, hide internals, log with context |\n\n## Security Code Review Checklist\n\nWhen reviewing code, check for these issues:\n\n### Input Handling\n- [ ] All user input validated server-side\n- [ ] Using parameterized queries (not string concatenation)\n- [ ] Input length limits enforced\n- [ ] Allowlist validation preferred over denylist\n\n### Authentication & Sessions\n- [ ] Passwords hashed with Argon2\u002Fbcrypt (not MD5\u002FSHA1)\n- [ ] Session tokens have sufficient entropy (128+ bits)\n- [ ] Sessions invalidated on logout\n- [ ] MFA available for sensitive operations\n\n### Access Control\n- [ ] Authorization checked on every request\n- [ ] Using object references user cannot manipulate\n- [ ] Deny by default policy\n- [ ] Privilege escalation paths reviewed\n\n### Data Protection\n- [ ] Sensitive data encrypted at rest\n- [ ] TLS for all data in transit\n- [ ] No sensitive data in URLs\u002Flogs\n- [ ] Secrets in environment\u002Fvault (not code)\n\n### Error Handling\n- [ ] No stack traces exposed to users\n- [ ] Fail-closed on errors (deny, not allow)\n- [ ] All exceptions logged with context\n- [ ] Consistent error responses (no enumeration)\n\n## Secure Code Patterns\n\n### SQL Injection Prevention\n```python\n# UNSAFE\ncursor.execute(f\"SELECT * FROM users WHERE id = {user_id}\")\n\n# SAFE\ncursor.execute(\"SELECT * FROM users WHERE id = %s\", (user_id,))\n```\n\n### Command Injection Prevention\n```python\n# UNSAFE\nos.system(f\"convert {filename} output.png\")\n\n# SAFE\nsubprocess.run([\"convert\", filename, \"output.png\"], shell=False)\n```\n\n### Password Storage\n```python\n# UNSAFE\nhashlib.md5(password.encode()).hexdigest()\n\n# SAFE\nfrom argon2 import PasswordHasher\nPasswordHasher().hash(password)\n```\n\n### Access Control\n```python\n# UNSAFE - No authorization check\n@app.route('\u002Fapi\u002Fuser\u002F\u003Cuser_id>')\ndef get_user(user_id):\n    return db.get_user(user_id)\n\n# SAFE - Authorization enforced\n@app.route('\u002Fapi\u002Fuser\u002F\u003Cuser_id>')\n@login_required\ndef get_user(user_id):\n    if current_user.id != user_id and not current_user.is_admin:\n        abort(403)\n    return db.get_user(user_id)\n```\n\n### Error Handling\n```python\n# UNSAFE - Exposes internals\n@app.errorhandler(Exception)\ndef handle_error(e):\n    return str(e), 500\n\n# SAFE - Fail-closed, log context\n@app.errorhandler(Exception)\ndef handle_error(e):\n    error_id = uuid.uuid4()\n    logger.exception(f\"Error {error_id}: {e}\")\n    return {\"error\": \"An error occurred\", \"id\": str(error_id)}, 500\n```\n\n### Fail-Closed Pattern\n```python\n# UNSAFE - Fail-open\ndef check_permission(user, resource):\n    try:\n        return auth_service.check(user, resource)\n    except Exception:\n        return True  # DANGEROUS!\n\n# SAFE - Fail-closed\ndef check_permission(user, resource):\n    try:\n        return auth_service.check(user, resource)\n    except Exception as e:\n        logger.error(f\"Auth check failed: {e}\")\n        return False  # Deny on error\n```\n\n## Agentic AI Security (OWASP 2026)\n\nWhen building or reviewing AI agent systems, check for:\n\n| Risk | Description | Mitigation |\n|------|-------------|------------|\n| ASI01: Goal Hijack | Prompt injection alters agent objectives | Input sanitization, goal boundaries, behavioral monitoring |\n| ASI02: Tool Misuse | Tools used in unintended ways | Least privilege, fine-grained permissions, validate I\u002FO |\n| ASI03: Privilege Abuse | Credential escalation across agents | Short-lived scoped tokens, identity verification |\n| ASI04: Supply Chain | Compromised plugins\u002FMCP servers | Verify signatures, sandbox, allowlist plugins |\n| ASI05: Code Execution | Unsafe code generation\u002Fexecution | Sandbox execution, static analysis, human approval |\n| ASI06: Memory Poisoning | Corrupted RAG\u002Fcontext data | Validate stored content, segment by trust level |\n| ASI07: Agent Comms | Spoofing between agents | Authenticate, encrypt, verify message integrity |\n| ASI08: Cascading Failures | Errors propagate across systems | Circuit breakers, graceful degradation, isolation |\n| ASI09: Trust Exploitation | Social engineering via AI | Label AI content, user education, verification steps |\n| ASI10: Rogue Agents | Compromised agents acting maliciously | Behavior monitoring, kill switches, anomaly detection |\n\n### Agent Security Checklist\n\n- [ ] All agent inputs sanitized and validated\n- [ ] Tools operate with minimum required permissions\n- [ ] Credentials are short-lived and scoped\n- [ ] Third-party plugins verified and sandboxed\n- [ ] Code execution happens in isolated environments\n- [ ] Agent communications authenticated and encrypted\n- [ ] Circuit breakers between agent components\n- [ ] Human approval for sensitive operations\n- [ ] Behavior monitoring for anomaly detection\n- [ ] Kill switch available for agent systems\n\n## ASVS 5.0 Key Requirements\n\n### Level 1 (All Applications)\n- Passwords minimum 12 characters\n- Check against breached password lists\n- Rate limiting on authentication\n- Session tokens 128+ bits entropy\n- HTTPS everywhere\n\n### Level 2 (Sensitive Data)\n- All L1 requirements plus:\n- MFA for sensitive operations\n- Cryptographic key management\n- Comprehensive security logging\n- Input validation on all parameters\n\n### Level 3 (Critical Systems)\n- All L1\u002FL2 requirements plus:\n- Hardware security modules for keys\n- Threat modeling documentation\n- Advanced monitoring and alerting\n- Penetration testing validation\n\n## Language-Specific Security Quirks\n\n> **Important:** The examples below are illustrative starting points, not exhaustive. When reviewing code, think like a senior security researcher: consider the language's memory model, type system, standard library pitfalls, ecosystem-specific attack vectors, and historical CVE patterns. Each language has deeper quirks beyond what's listed here.\n\nDifferent languages have unique security pitfalls. Here are the top 20 languages with key security considerations. **Go deeper for the specific language you're working in:**\n\n---\n\n### JavaScript \u002F TypeScript\n**Main Risks:** Prototype pollution, XSS, eval injection\n```javascript\n\u002F\u002F UNSAFE: Prototype pollution\nObject.assign(target, userInput)\n\u002F\u002F SAFE: Use null prototype or validate keys\nObject.assign(Object.create(null), validated)\n\n\u002F\u002F UNSAFE: eval injection\neval(userCode)\n\u002F\u002F SAFE: Never use eval with user input\n```\n**Watch for:** `eval()`, `innerHTML`, `document.write()`, prototype chain manipulation, `__proto__`\n\n---\n\n### Python\n**Main Risks:** Pickle deserialization, format string injection, shell injection\n```python\n# UNSAFE: Pickle RCE\npickle.loads(user_data)\n# SAFE: Use JSON or validate source\njson.loads(user_data)\n\n# UNSAFE: Format string injection\nquery = \"SELECT * FROM users WHERE name = '%s'\" % user_input\n# SAFE: Parameterized\ncursor.execute(\"SELECT * FROM users WHERE name = %s\", (user_input,))\n```\n**Watch for:** `pickle`, `eval()`, `exec()`, `os.system()`, `subprocess` with `shell=True`\n\n---\n\n### Java\n**Main Risks:** Deserialization RCE, XXE, JNDI injection\n```java\n\u002F\u002F UNSAFE: Arbitrary deserialization\nObjectInputStream ois = new ObjectInputStream(userStream);\nObject obj = ois.readObject();\n\n\u002F\u002F SAFE: Use allowlist or JSON\nObjectMapper mapper = new ObjectMapper();\nmapper.readValue(json, SafeClass.class);\n```\n**Watch for:** `ObjectInputStream`, `Runtime.exec()`, XML parsers without XXE protection, JNDI lookups\n\n---\n\n### C#\n**Main Risks:** Deserialization, SQL injection, path traversal\n```csharp\n\u002F\u002F UNSAFE: BinaryFormatter RCE\nBinaryFormatter bf = new BinaryFormatter();\nobject obj = bf.Deserialize(stream);\n\n\u002F\u002F SAFE: Use System.Text.Json\nvar obj = JsonSerializer.Deserialize\u003CSafeType>(json);\n```\n**Watch for:** `BinaryFormatter`, `JavaScriptSerializer`, `TypeNameHandling.All`, raw SQL strings\n\n---\n\n### PHP\n**Main Risks:** Type juggling, file inclusion, object injection\n```php\n\u002F\u002F UNSAFE: Type juggling in auth\nif ($password == $stored_hash) { ... }\n\u002F\u002F SAFE: Use strict comparison\nif (hash_equals($stored_hash, $password)) { ... }\n\n\u002F\u002F UNSAFE: File inclusion\ninclude($_GET['page'] . '.php');\n\u002F\u002F SAFE: Allowlist pages\n$allowed = ['home', 'about']; include(in_array($page, $allowed) ? \"$page.php\" : 'home.php');\n```\n**Watch for:** `==` vs `===`, `include\u002Frequire`, `unserialize()`, `preg_replace` with `\u002Fe`, `extract()`\n\n---\n\n### Go\n**Main Risks:** Race conditions, template injection, slice bounds\n```go\n\u002F\u002F UNSAFE: Race condition\ngo func() { counter++ }()\n\u002F\u002F SAFE: Use sync primitives\natomic.AddInt64(&counter, 1)\n\n\u002F\u002F UNSAFE: Template injection\ntemplate.HTML(userInput)\n\u002F\u002F SAFE: Let template escape\n{{.UserInput}}\n```\n**Watch for:** Goroutine data races, `template.HTML()`, `unsafe` package, unchecked slice access\n\n---\n\n### Ruby\n**Main Risks:** Mass assignment, YAML deserialization, regex DoS\n```ruby\n# UNSAFE: Mass assignment\nUser.new(params[:user])\n# SAFE: Strong parameters\nUser.new(params.require(:user).permit(:name, :email))\n\n# UNSAFE: YAML RCE\nYAML.load(user_input)\n# SAFE: Use safe_load\nYAML.safe_load(user_input)\n```\n**Watch for:** YAML.load, Marshal.load, eval, send with user input, .permit!\n\n---\n\n### Rust\n**Main Risks:** Unsafe blocks, FFI boundary issues, integer overflow in release\n```rust\n\u002F\u002F CAUTION: Unsafe bypasses safety\nunsafe { ptr::read(user_ptr) }\n\n\u002F\u002F CAUTION: Release integer overflow\nlet x: u8 = 255;\nlet y = x + 1; \u002F\u002F Wraps to 0 in release!\n\u002F\u002F SAFE: Use checked arithmetic\nlet y = x.checked_add(1).unwrap_or(255);\n```\n**Watch for:** `unsafe` blocks, FFI calls, integer overflow in release builds, `.unwrap()` on untrusted input\n\n---\n\n### Swift\n**Main Risks:** Force unwrapping crashes, Objective-C interop\n```swift\n\u002F\u002F UNSAFE: Force unwrap on untrusted data\nlet value = jsonDict[\"key\"]!\n\u002F\u002F SAFE: Safe unwrapping\nguard let value = jsonDict[\"key\"] else { return }\n\n\u002F\u002F UNSAFE: Format string\nString(format: userInput, args)\n\u002F\u002F SAFE: Don't use user input as format\n```\n**Watch for:** force unwrap (!), try!, ObjC bridging, NSSecureCoding misuse\n\n---\n\n### Kotlin\n**Main Risks:** Null safety bypass, Java interop, serialization\n```kotlin\n\u002F\u002F UNSAFE: Platform type from Java\nval len = javaString.length \u002F\u002F NPE if null\n\u002F\u002F SAFE: Explicit null check\nval len = javaString?.length ?: 0\n\n\u002F\u002F UNSAFE: Reflection\nclazz.getDeclaredMethod(userInput)\n\u002F\u002F SAFE: Allowlist methods\n```\n**Watch for:** Java interop nulls (! operator), reflection, serialization, platform types\n\n---\n\n### C \u002F C++\n**Main Risks:** Buffer overflow, use-after-free, format string\n```c\n\u002F\u002F UNSAFE: Buffer overflow\nchar buf[10]; strcpy(buf, userInput);\n\u002F\u002F SAFE: Bounds checking\nstrncpy(buf, userInput, sizeof(buf) - 1);\n\n\u002F\u002F UNSAFE: Format string\nprintf(userInput);\n\u002F\u002F SAFE: Always use format specifier\nprintf(\"%s\", userInput);\n```\n**Watch for:** `strcpy`, `sprintf`, `gets`, pointer arithmetic, manual memory management, integer overflow\n\n---\n\n### Scala\n**Main Risks:** XML external entities, serialization, pattern matching exhaustiveness\n```scala\n\u002F\u002F UNSAFE: XXE\nval xml = XML.loadString(userInput)\n\u002F\u002F SAFE: Disable external entities\nval factory = SAXParserFactory.newInstance()\nfactory.setFeature(\"http:\u002F\u002Fxml.org\u002Fsax\u002Ffeatures\u002Fexternal-general-entities\", false)\n```\n**Watch for:** Java interop issues, XML parsing, `Serializable`, exhaustive pattern matching\n\n---\n\n### R\n**Main Risks:** Code injection, file path manipulation\n```r\n# UNSAFE: eval injection\neval(parse(text = user_input))\n# SAFE: Never parse user input as code\n\n# UNSAFE: Path traversal\nread.csv(paste0(\"data\u002F\", user_file))\n# SAFE: Validate filename\nif (grepl(\"^[a-zA-Z0-9]+\\\\.csv$\", user_file)) read.csv(...)\n```\n**Watch for:** `eval()`, `parse()`, `source()`, `system()`, file path manipulation\n\n---\n\n### Perl\n**Main Risks:** Regex injection, open() injection, taint mode bypass\n```perl\n# UNSAFE: Regex DoS\n$input =~ \u002F$user_pattern\u002F;\n# SAFE: Use quotemeta\n$input =~ \u002F\\Q$user_pattern\\E\u002F;\n\n# UNSAFE: open() command injection\nopen(FILE, $user_file);\n# SAFE: Three-argument open\nopen(my $fh, '\u003C', $user_file);\n```\n**Watch for:** Two-arg `open()`, regex from user input, backticks, `eval`, disabled taint mode\n\n---\n\n### Shell (Bash)\n**Main Risks:** Command injection, word splitting, globbing\n```bash\n# UNSAFE: Unquoted variables\nrm $user_file\n# SAFE: Always quote\nrm \"$user_file\"\n\n# UNSAFE: eval\neval \"$user_command\"\n# SAFE: Never eval user input\n```\n**Watch for:** Unquoted variables, `eval`, backticks, `$(...)` with user input, missing `set -euo pipefail`\n\n---\n\n### Lua\n**Main Risks:** Sandbox escape, loadstring injection\n```lua\n-- UNSAFE: Code injection\nloadstring(user_code)()\n-- SAFE: Use sandboxed environment with restricted functions\n```\n**Watch for:** `loadstring`, `loadfile`, `dofile`, `os.execute`, `io` library, debug library\n\n---\n\n### Elixir\n**Main Risks:** Atom exhaustion, code injection, ETS access\n```elixir\n# UNSAFE: Atom exhaustion DoS\nString.to_atom(user_input)\n# SAFE: Use existing atoms only\nString.to_existing_atom(user_input)\n\n# UNSAFE: Code injection\nCode.eval_string(user_input)\n# SAFE: Never eval user input\n```\n**Watch for:** `String.to_atom`, `Code.eval_string`, `:erlang.binary_to_term`, ETS public tables\n\n---\n\n### Dart \u002F Flutter\n**Main Risks:** Platform channel injection, insecure storage\n```dart\n\u002F\u002F UNSAFE: Storing secrets in SharedPreferences\nprefs.setString('auth_token', token);\n\u002F\u002F SAFE: Use flutter_secure_storage\nsecureStorage.write(key: 'auth_token', value: token);\n```\n**Watch for:** Platform channel data, `dart:mirrors`, `Function.apply`, insecure local storage\n\n---\n\n### PowerShell\n**Main Risks:** Command injection, execution policy bypass\n```powershell\n# UNSAFE: Injection\nInvoke-Expression $userInput\n# SAFE: Avoid Invoke-Expression with user data\n\n# UNSAFE: Unvalidated path\nGet-Content $userPath\n# SAFE: Validate path is within allowed directory\n```\n**Watch for:** `Invoke-Expression`, `& $userVar`, `Start-Process` with user args, `-ExecutionPolicy Bypass`\n\n---\n\n### SQL (All Dialects)\n**Main Risks:** Injection, privilege escalation, data exfiltration\n```sql\n-- UNSAFE: String concatenation\n\"SELECT * FROM users WHERE id = \" + userId\n\n-- SAFE: Parameterized query (language-specific)\n-- Use prepared statements in ALL cases\n```\n**Watch for:** Dynamic SQL, `EXECUTE IMMEDIATE`, stored procedures with dynamic queries, privilege grants\n\n---\n\n## Deep Security Analysis Mindset\n\nWhen reviewing any language, think like a senior security researcher:\n\n1. **Memory Model:** How does the language handle memory? Managed vs manual? GC pauses exploitable?\n2. **Type System:** Weak typing = type confusion attacks. Look for coercion exploits.\n3. **Serialization:** Every language has its pickle\u002FMarshal equivalent. All are dangerous.\n4. **Concurrency:** Race conditions, TOCTOU, atomicity failures specific to the threading model.\n5. **FFI Boundaries:** Native interop is where type safety breaks down.\n6. **Standard Library:** Historic CVEs in std libs (Python urllib, Java XML, Ruby OpenSSL).\n7. **Package Ecosystem:** Typosquatting, dependency confusion, malicious packages.\n8. **Build System:** Makefile\u002Fgradle\u002Fnpm script injection during builds.\n9. **Runtime Behavior:** Debug vs release differences (Rust overflow, C++ assertions).\n10. **Error Handling:** How does the language fail? Silently? With stack traces? Fail-open?\n\n**For any language not listed:** Research its specific CWE patterns, CVE history, and known footguns. The examples above are entry points, not complete coverage.\n\n## When to Apply This Skill\n\nUse this skill when:\n- Writing authentication or authorization code\n- Handling user input or external data\n- Implementing cryptography or password storage\n- Reviewing code for security vulnerabilities\n- Designing API endpoints\n- Building AI agent systems\n- Configuring application security settings\n- Handling errors and exceptions\n- Working with third-party dependencies\n- **Working in any language** - apply the deep analysis mindset above\n","# OWASP Security Best Practices Skill\n\nApply these security standards when writing or reviewing code.\n\n## Quick Reference: OWASP Top 10:2025\n\n| # | Vulnerability | Key Prevention |\n|---|---------------|----------------|\n| A01 | Broken Access Control | Deny by default, enforce server-side, verify ownership |\n| A02 | Security Misconfiguration | Harden configs, disable defaults, minimize features |\n| A03 | Supply Chain Failures | Lock versions, verify integrity, audit dependencies |\n| A04 | Cryptographic Failures | TLS 1.2+, AES-256-GCM, Argon2\u002Fbcrypt for passwords |\n| A05 | Injection | Parameterized queries, input validation, safe APIs |\n| A06 | Insecure Design | Threat model, rate limit, design security controls |\n| A07 | Auth Failures | MFA, check breached passwords, secure sessions |\n| A08 | Integrity Failures | Sign packages, SRI for CDN, safe serialization |\n| A09 | Logging Failures | Log security events, structured format, alerting |\n| A10 | Exception Handling | Fail-closed, hide internals, log with context |\n\n## Security Code Review Checklist\n\nWhen reviewing code, check for these issues:\n\n### Input Handling\n- [ ] All user input validated server-side\n- [ ] Using parameterized queries (not string concatenation)\n- [ ] Input length limits enforced\n- [ ] Allowlist validation preferred over denylist\n\n### Authentication & Sessions\n- [ ] Passwords hashed with Argon2\u002Fbcrypt (not MD5\u002FSHA1)\n- [ ] Session tokens have sufficient entropy (128+ bits)\n- [ ] Sessions invalidated on logout\n- [ ] MFA available for sensitive operations\n\n### Access Control\n- [ ] Authorization checked on every request\n- [ ] Using object references user cannot manipulate\n- [ ] Deny by default policy\n- [ ] Privilege escalation paths reviewed\n\n### Data Protection\n- [ ] Sensitive data encrypted at rest\n- [ ] TLS for all data in transit\n- [ ] No sensitive data in URLs\u002Flogs\n- [ ] Secrets in environment\u002Fvault (not code)\n\n### Error Handling\n- [ ] No stack traces exposed to users\n- [ ] Fail-closed on errors (deny, not allow)\n- [ ] All exceptions logged with context\n- [ ] Consistent error responses (no enumeration)\n\n## Secure Code Patterns\n\n### SQL Injection Prevention\n```python\n# UNSAFE\ncursor.execute(f\"SELECT * FROM users WHERE id = {user_id}\")\n\n# SAFE\ncursor.execute(\"SELECT * FROM users WHERE id = %s\", (user_id,))\n```\n\n### Command Injection Prevention\n```python\n# UNSAFE\nos.system(f\"convert {filename} output.png\")\n\n# SAFE\nsubprocess.run([\"convert\", filename, \"output.png\"], shell=False)\n```\n\n### Password Storage\n```python\n# UNSAFE\nhashlib.md5(password.encode()).hexdigest()\n\n# SAFE\nfrom argon2 import PasswordHasher\nPasswordHasher().hash(password)\n```\n\n### Access Control\n```python\n# UNSAFE - No authorization check\n@app.route('\u002Fapi\u002Fuser\u002F\u003Cuser_id>')\ndef get_user(user_id):\n    return db.get_user(user_id)\n\n# SAFE - Authorization enforced\n@app.route('\u002Fapi\u002Fuser\u002F\u003Cuser_id>')\n@login_required\ndef get_user(user_id):\n    if current_user.id != user_id and not current_user.is_admin:\n        abort(403)\n    return db.get_user(user_id)\n```\n\n### Error Handling\n```python\n# UNSAFE - Exposes internals\n@app.errorhandler(Exception)\ndef handle_error(e):\n    return str(e), 500\n\n# SAFE - Fail-closed, log context\n@app.errorhandler(Exception)\ndef handle_error(e):\n    error_id = uuid.uuid4()\n    logger.exception(f\"Error {error_id}: {e}\")\n    return {\"error\": \"An error occurred\", \"id\": str(error_id)}, 500\n```\n\n### Fail-Closed Pattern\n```python\n# UNSAFE - Fail-open\ndef check_permission(user, resource):\n    try:\n        return auth_service.check(user, resource)\n    except Exception:\n        return True  # DANGEROUS!\n\n# SAFE - Fail-closed\ndef check_permission(user, resource):\n    try:\n        return auth_service.check(user, resource)\n    except Exception as e:\n        logger.error(f\"Auth check failed: {e}\")\n        return False  # Deny on error\n```\n\n## Agentic AI Security (OWASP 2026)\n\nWhen building or reviewing AI agent systems, check for:\n\n| Risk | Description | Mitigation |\n|------|-------------|------------|\n| ASI01: Goal Hijack | Prompt injection alters agent objectives | Input sanitization, goal boundaries, behavioral monitoring |\n| ASI02: Tool Misuse | Tools used in unintended ways | Least privilege, fine-grained permissions, validate I\u002FO |\n| ASI03: Privilege Abuse | Credential escalation across agents | Short-lived scoped tokens, identity verification |\n| ASI04: Supply Chain | Compromised plugins\u002FMCP servers | Verify signatures, sandbox, allowlist plugins |\n| ASI05: Code Execution | Unsafe code generation\u002Fexecution | Sandbox execution, static analysis, human approval |\n| ASI06: Memory Poisoning | Corrupted RAG\u002Fcontext data | Validate stored content, segment by trust level |\n| ASI07: Agent Comms | Spoofing between agents | Authenticate, encrypt, verify message integrity |\n| ASI08: Cascading Failures | Errors propagate across systems | Circuit breakers, graceful degradation, isolation |\n| ASI09: Trust Exploitation | Social engineering via AI | Label AI content, user education, verification steps |\n| ASI10: Rogue Agents | Compromised agents acting maliciously | Behavior monitoring, kill switches, anomaly detection |\n\n### Agent Security Checklist\n\n- [ ] All agent inputs sanitized and validated\n- [ ] Tools operate with minimum required permissions\n- [ ] Credentials are short-lived and scoped\n- [ ] Third-party plugins verified and sandboxed\n- [ ] Code execution happens in isolated environments\n- [ ] Agent communications authenticated and encrypted\n- [ ] Circuit breakers between agent components\n- [ ] Human approval for sensitive operations\n- [ ] Behavior monitoring for anomaly detection\n- [ ] Kill switch available for agent systems\n\n## ASVS 5.0 Key Requirements\n\n### Level 1 (All Applications)\n- Passwords minimum 12 characters\n- Check against breached password lists\n- Rate limiting on authentication\n- Session tokens 128+ bits entropy\n- HTTPS everywhere\n\n### Level 2 (Sensitive Data)\n- All L1 requirements plus:\n- MFA for sensitive operations\n- Cryptographic key management\n- Comprehensive security logging\n- Input validation on all parameters\n\n### Level 3 (Critical Systems)\n- All L1\u002FL2 requirements plus:\n- Hardware security modules for keys\n- Threat modeling documentation\n- Advanced monitoring and alerting\n- Penetration testing validation\n\n## Language-Specific Security Quirks\n\n> **Important:** The examples below are illustrative starting points, not exhaustive. When reviewing code, think like a senior security researcher: consider the language's memory model, type system, standard library pitfalls, ecosystem-specific attack vectors, and historical CVE patterns. Each language has deeper quirks beyond what's listed here.\n\nDifferent languages have unique security pitfalls. Here are the top 20 languages with key security considerations. **Go deeper for the specific language you're working in:**\n\n---\n\n### JavaScript \u002F TypeScript\n**Main Risks:** Prototype pollution, XSS, eval injection\n```javascript\n\u002F\u002F UNSAFE: Prototype pollution\nObject.assign(target, userInput)\n\u002F\u002F SAFE: Use null prototype or validate keys\nObject.assign(Object.create(null), validated)\n\n\u002F\u002F UNSAFE: eval injection\neval(userCode)\n\u002F\u002F SAFE: Never use eval with user input\n```\n**Watch for:** `eval()`, `innerHTML`, `document.write()`, prototype chain manipulation, `__proto__`\n\n---\n\n### Python\n**Main Risks:** Pickle deserialization, format string injection, shell injection\n```python\n# UNSAFE: Pickle RCE\npickle.loads(user_data)\n# SAFE: Use JSON or validate source\njson.loads(user_data)\n\n# UNSAFE: Format string injection\nquery = \"SELECT * FROM users WHERE name = '%s'\" % user_input\n# SAFE: Parameterized\ncursor.execute(\"SELECT * FROM users WHERE name = %s\", (user_input,))\n```\n**Watch for:** `pickle`, `eval()`, `exec()`, `os.system()`, `subprocess` with `shell=True`\n\n---\n\n### Java\n**Main Risks:** Deserialization RCE, XXE, JNDI injection\n```java\n\u002F\u002F UNSAFE: Arbitrary deserialization\nObjectInputStream ois = new ObjectInputStream(userStream);\nObject obj = ois.readObject();\n\n\u002F\u002F SAFE: Use allowlist or JSON\nObjectMapper mapper = new ObjectMapper();\nmapper.readValue(json, SafeClass.class);\n```\n**Watch for:** `ObjectInputStream`, `Runtime.exec()`, XML parsers without XXE protection, JNDI lookups\n\n---\n\n### C#\n**Main Risks:** Deserialization, SQL injection, path traversal\n```csharp\n\u002F\u002F UNSAFE: BinaryFormatter RCE\nBinaryFormatter bf = new BinaryFormatter();\nobject obj = bf.Deserialize(stream);\n\n\u002F\u002F SAFE: Use System.Text.Json\nvar obj = JsonSerializer.Deserialize\u003CSafeType>(json);\n```\n**Watch for:** `BinaryFormatter`, `JavaScriptSerializer`, `TypeNameHandling.All`, raw SQL strings\n\n---\n\n### PHP\n**Main Risks:** Type juggling, file inclusion, object injection\n```php\n\u002F\u002F UNSAFE: Type juggling in auth\nif ($password == $stored_hash) { ... }\n\u002F\u002F SAFE: Use strict comparison\nif (hash_equals($stored_hash, $password)) { ... }\n\n\u002F\u002F UNSAFE: File inclusion\ninclude($_GET['page'] . '.php');\n\u002F\u002F SAFE: Allowlist pages\n$allowed = ['home', 'about']; include(in_array($page, $allowed) ? \"$page.php\" : 'home.php');\n```\n**Watch for:** `==` vs `===`, `include\u002Frequire`, `unserialize()`, `preg_replace` with `\u002Fe`, `extract()`\n\n---\n\n### Go\n**Main Risks:** Race conditions, template injection, slice bounds\n```go\n\u002F\u002F UNSAFE: Race condition\ngo func() { counter++ }()\n\u002F\u002F SAFE: Use sync primitives\natomic.AddInt64(&counter, 1)\n\n\u002F\u002F UNSAFE: Template injection\ntemplate.HTML(userInput)\n\u002F\u002F SAFE: Let template escape\n{{.UserInput}}\n```\n**Watch for:** Goroutine data races, `template.HTML()`, `unsafe` package, unchecked slice access\n\n---\n\n### Ruby\n**Main Risks:** Mass assignment, YAML deserialization, regex DoS\n```ruby\n# UNSAFE: Mass assignment\nUser.new(params[:user])\n# SAFE: Strong parameters\nUser.new(params.require(:user).permit(:name, :email))\n\n# UNSAFE: YAML RCE\nYAML.load(user_input)\n# SAFE: Use safe_load\nYAML.safe_load(user_input)\n```\n**Watch for:** YAML.load, Marshal.load, eval, send with user input, .permit!\n\n---\n\n### Rust\n**Main Risks:** Unsafe blocks, FFI boundary issues, integer overflow in release\n```rust\n\u002F\u002F CAUTION: Unsafe bypasses safety\nunsafe { ptr::read(user_ptr) }\n\n\u002F\u002F CAUTION: Release integer overflow\nlet x: u8 = 255;\nlet y = x + 1; \u002F\u002F Wraps to 0 in release!\n\u002F\u002F SAFE: Use checked arithmetic\nlet y = x.checked_add(1).unwrap_or(255);\n```\n**Watch for:** `unsafe` blocks, FFI calls, integer overflow in release builds, `.unwrap()` on untrusted input\n\n---\n\n### Swift\n**Main Risks:** Force unwrapping crashes, Objective-C interop\n```swift\n\u002F\u002F UNSAFE: Force unwrap on untrusted data\nlet value = jsonDict[\"key\"]!\n\u002F\u002F SAFE: Safe unwrapping\nguard let value = jsonDict[\"key\"] else { return }\n\n\u002F\u002F UNSAFE: Format string\nString(format: userInput, args)\n\u002F\u002F SAFE: Don't use user input as format\n```\n**Watch for:** force unwrap (!), try!, ObjC bridging, NSSecureCoding misuse\n\n---\n\n### Kotlin\n**Main Risks:** Null safety bypass, Java interop, serialization\n```kotlin\n\u002F\u002F UNSAFE: Platform type from Java\nval len = javaString.length \u002F\u002F NPE if null\n\u002F\u002F SAFE: Explicit null check\nval len = javaString?.length ?: 0\n\n\u002F\u002F UNSAFE: Reflection\nclazz.getDeclaredMethod(userInput)\n\u002F\u002F SAFE: Allowlist methods\n```\n**Watch for:** Java interop nulls (! operator), reflection, serialization, platform types\n\n---\n\n### C \u002F C++\n**Main Risks:** Buffer overflow, use-after-free, format string\n```c\n\u002F\u002F UNSAFE: Buffer overflow\nchar buf[10]; strcpy(buf, userInput);\n\u002F\u002F SAFE: Bounds checking\nstrncpy(buf, userInput, sizeof(buf) - 1);\n\n\u002F\u002F UNSAFE: Format string\nprintf(userInput);\n\u002F\u002F SAFE: Always use format specifier\nprintf(\"%s\", userInput);\n```\n**Watch for:** `strcpy`, `sprintf`, `gets`, pointer arithmetic, manual memory management, integer overflow\n\n---\n\n### Scala\n**Main Risks:** XML external entities, serialization, pattern matching exhaustiveness\n```scala\n\u002F\u002F UNSAFE: XXE\nval xml = XML.loadString(userInput)\n\u002F\u002F SAFE: Disable external entities\nval factory = SAXParserFactory.newInstance()\nfactory.setFeature(\"http:\u002F\u002Fxml.org\u002Fsax\u002Ffeatures\u002Fexternal-general-entities\", false)\n```\n**Watch for:** Java interop issues, XML parsing, `Serializable`, exhaustive pattern matching\n\n---\n\n### R\n**Main Risks:** Code injection, file path manipulation\n```r\n# UNSAFE: eval injection\neval(parse(text = user_input))\n# SAFE: Never parse user input as code\n\n# UNSAFE: Path traversal\nread.csv(paste0(\"data\u002F\", user_file))\n# SAFE: Validate filename\nif (grepl(\"^[a-zA-Z0-9]+\\\\.csv$\", user_file)) read.csv(...)\n```\n**Watch for:** `eval()`, `parse()`, `source()`, `system()`, file path manipulation\n\n---\n\n### Perl\n**Main Risks:** Regex injection, open() injection, taint mode bypass\n```perl\n# UNSAFE: Regex DoS\n$input =~ \u002F$user_pattern\u002F;\n# SAFE: Use quotemeta\n$input =~ \u002F\\Q$user_pattern\\E\u002F;\n\n# UNSAFE: open() command injection\nopen(FILE, $user_file);\n# SAFE: Three-argument open\nopen(my $fh, '\u003C', $user_file);\n```\n**Watch for:** Two-arg `open()`, regex from user input, backticks, `eval`, disabled taint mode\n\n---\n\n### Shell (Bash)\n**Main Risks:** Command injection, word splitting, globbing\n```bash\n# UNSAFE: Unquoted variables\nrm $user_file\n# SAFE: Always quote\nrm \"$user_file\"\n\n# UNSAFE: eval\neval \"$user_command\"\n# SAFE: Never eval user input\n```\n**Watch for:** Unquoted variables, `eval`, backticks, `$(...)` with user input, missing `set -euo pipefail`\n\n---\n\n### Lua\n**Main Risks:** Sandbox escape, loadstring injection\n```lua\n-- UNSAFE: Code injection\nloadstring(user_code)()\n-- SAFE: Use sandboxed environment with restricted functions\n```\n**Watch for:** `loadstring`, `loadfile`, `dofile`, `os.execute`, `io` library, debug library\n\n---\n\n### Elixir\n**Main Risks:** Atom exhaustion, code injection, ETS access\n```elixir\n# UNSAFE: Atom exhaustion DoS\nString.to_atom(user_input)\n# SAFE: Use existing atoms only\nString.to_existing_atom(user_input)\n\n# UNSAFE: Code injection\nCode.eval_string(user_input)\n# SAFE: Never eval user input\n```\n**Watch for:** `String.to_atom`, `Code.eval_string`, `:erlang.binary_to_term`, ETS public tables\n\n---\n\n### Dart \u002F Flutter\n**Main Risks:** Platform channel injection, insecure storage\n```dart\n\u002F\u002F UNSAFE: Storing secrets in SharedPreferences\nprefs.setString('auth_token', token);\n\u002F\u002F SAFE: Use flutter_secure_storage\nsecureStorage.write(key: 'auth_token', value: token);\n```\n**Watch for:** Platform channel data, `dart:mirrors`, `Function.apply`, insecure local storage\n\n---\n\n### PowerShell\n**Main Risks:** Command injection, execution policy bypass\n```powershell\n# UNSAFE: Injection\nInvoke-Expression $userInput\n# SAFE: Avoid Invoke-Expression with user data\n\n# UNSAFE: Unvalidated path\nGet-Content $userPath\n# SAFE: Validate path is within allowed directory\n```\n**Watch for:** `Invoke-Expression`, `& $userVar`, `Start-Process` with user args, `-ExecutionPolicy Bypass`\n\n---\n\n### SQL (All Dialects)\n**Main Risks:** Injection, privilege escalation, data exfiltration\n```sql\n-- UNSAFE: String concatenation\n\"SELECT * FROM users WHERE id = \" + userId\n\n-- SAFE: Parameterized query (language-specific)\n-- Use prepared statements in ALL cases\n```\n**Watch for:** Dynamic SQL, `EXECUTE IMMEDIATE`, stored procedures with dynamic queries, privilege grants\n\n---\n\n## Deep Security Analysis Mindset\n\nWhen reviewing any language, think like a senior security researcher:\n\n1. **Memory Model:** How does the language handle memory? Managed vs manual? GC pauses exploitable?\n2. **Type System:** Weak typing = type confusion attacks. Look for coercion exploits.\n3. **Serialization:** Every language has its pickle\u002FMarshal equivalent. All are dangerous.\n4. **Concurrency:** Race conditions, TOCTOU, atomicity failures specific to the threading model.\n5. **FFI Boundaries:** Native interop is where type safety breaks down.\n6. **Standard Library:** Historic CVEs in std libs (Python urllib, Java XML, Ruby OpenSSL).\n7. **Package Ecosystem:** Typosquatting, dependency confusion, malicious packages.\n8. **Build System:** Makefile\u002Fgradle\u002Fnpm script injection during builds.\n9. **Runtime Behavior:** Debug vs release differences (Rust overflow, C++ assertions).\n10. **Error Handling:** How does the language fail? Silently? With stack traces? Fail-open?\n\n**For any language not listed:** Research its specific CWE patterns, CVE history, and known footguns. The examples above are entry points, not complete coverage.\n\n## When to Apply This Skill\n\nUse this skill when:\n- Writing authentication or authorization code\n- Handling user input or external data\n- Implementing cryptography or password storage\n- Reviewing code for security vulnerabilities\n- Designing API endpoints\n- Building AI agent systems\n- Configuring application security settings\n- Handling errors and exceptions\n- Working with third-party dependencies\n- **Working in any language** - apply the deep analysis mindset above\n",{"name":5,"description":7},"main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FSecurity & Web Testing\u002Fowasp-security",13,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one","http:\u002F\u002Fhuangchiyu.com\u002FSKILLS_All-in-one\u002F","https:\u002F\u002Fgithub.com\u002Feric861129","https:\u002F\u002Fhuangchiyu.com\u002FChiYu-Blog\u002F","開發工程師，專注於 C#／.NET 系統現代化、AI-assisted engineering、開源工具與技術寫作。","2026-04-16 14:28:14",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill owasp-security",{"tool":66,"command":67},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill owasp-security",{"tool":69,"command":70},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill owasp-security","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FSecurity & Web Testing\u002Fowasp-security\u002FSKILL.md",true,[],[75,103,134,159,183,203],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":82,"publishedAt":45},"01M6CZ1WR3KNVTKSWH4GNWT646","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fwhat-if-oracle\u002FSKILL.md",[81],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"oracle","what if oracle","go","run","planning","ux","futures","risk","analysis","explore","decision","branch","question","read","write","idea","exploration","options","stress-test","strategies",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":119,"publishedAt":45},"01M6CZ1QHGJE91A95MSN5EK5Q9","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fvenue-templates\u002FSKILL.md",[109,112,115,116],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":117,"categoryName":118,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[120,121,122,123,124,125,126,127,128,129,96,97,130,131,132,133],"templates","venue templates","research","guidelines","NeurIPS","ICML","LaTeX","science","Bash","access","edit","proposals","Academic","requirements",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":142,"publishedAt":45},"01M6CZ1KBQD2E5RTFB3BGVX7CD","the-fool","Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fthe-fool\u002FSKILL.md",[140,141],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[143,144,85,145,146,86,39,147,148,149,150,151,152,153,131,154,155,156,157,158],"the fool","review","workflow","architecture","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","expert","poke","ideas",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":168,"publishedAt":45},"01M6CZ1ES826S7P1X3333E40TA","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-writing\u002FSKILL.md",[165,166,167],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":117,"categoryName":118,"taxonomyType":26,"taxonomyTypeDesc":27},[169,170,123,171,172,173,174,175,128,176,96,97,130,43,177,178,179,180,181,182],"writing","scientific writing","core","reporting","deep research","Citations","Outlines","tool","never","structure","deep","full","stage","prisma",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":45},"01M6CZ1B2JGJTB9FRD0TW4RXXE","scientific-brainstorming","Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-brainstorming\u002FSKILL.md",[189],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[191,192,122,193,87,194,195,196,43,197,198,199,99,200,201,181,202],"brainstorming","scientific brainstorming","sessions","data","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":215,"publishedAt":45},"01M6CZ16JG8N7A2ZX04BGE8J2Y","research-lookup","Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fresearch-lookup\u002FSKILL.md",[209,212,213,214],{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[122,216,217,218,194,219,220,128,221,222,96,97,130,43,223,224,225,226,227,132],"lookup","research lookup","search","perplexity","api","parallel","openrouter","backend","up","look","queries","chat"]