[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSSY453K9DNGZCX3CZCZF5":3,"skill-same:01M7CSSY453K9DNGZCX3CZCZF5":49},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CSSY453K9DNGZCX3CZCZF5","security-review",null,"Use in code_review when the diff touches input handling, auth, queries, files, outbound requests, secrets, dependencies or LLM calls, and in analysis for any new endpoint or data flow","makifbaysal\u002Ftasktrooper","makifbaysal","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F25031940?v=4","01M7CRG3ZCSYZSSEVDMW3DEYC8","Mehmet Akif Baysal","01M7CRG401FJ8YAXH5ER730XYV",122,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fsystem-architect\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: security-review\ncategory: quality\ndescription: Use in code_review when the diff touches input handling, auth, queries, files, outbound requests, secrets, dependencies or LLM calls, and in analysis for any new endpoint or data flow\nsource: getsentry\u002Fskills find-bugs (Apache-2.0), anthropics\u002Fclaude-plugins-official (Apache-2.0), github\u002Fawesome-copilot se-security-reviewer (MIT), adapted; OWASP category names linked only\n---\n# Security Review\n\n## Overview\n\nSecurity is not a separate pass over the whole repo — it is one more lens on the diff (code_review) or the design (analysis) you are already reading. Report only what is reachable by an attacker; a theoretical issue with no path to it is noise that trains people to skip your findings.\n\n## 1. Risk Tier First\n\n- **High** — auth, payments, admin actions, file upload, outbound URL fetch, anything that calls an LLM with tool access. Run the full checklist below.\n- **Medium** — user data, external API calls. Run Injection, Authorization, Exceptional Conditions, Secrets.\n- **Low** — pure UI, utilities, pure config\u002Fcopy. Run Secrets and Supply Chain only.\n\n## 2. Map the Attack Surface (of the diff, not the repo)\n\nList, from the diff: every new input (params, headers, body, path segment, uploaded file, webhook payload, LLM output used downstream), every new or changed query, every auth\u002Fauthorization check, every outbound call, every secret touched.\n\n## 3. Report Only Attacker-Reachable Findings\n\nTrace the value to its source with `grep_code`\u002F`expand_symbol_context` before flagging it. **Not attacker-controlled:** config values, environment variables, constants, server-set values, test fixtures. **Not a finding:** framework auto-escaping doing its job (React `{x}`, an ORM's parameterized query) — that is the control working, not a gap.\n\n## 4. Checks\n\n**Authorization per new route** — does it carry the same middleware as its neighbours, and does the query filter by owner\u002Ftenant (IDOR)?\n- ❌ `func (h *Handler) GetInvoice(w, r) { id := r.PathValue(\"id\"); inv, _ := h.repo.Get(ctx, id); json.NewEncoder(w).Encode(inv) }` — any authenticated user reads any invoice by guessing an id.\n- ✅ `inv, err := h.repo.Get(ctx, id); if inv.OrgID != authctx.OrgID(ctx) { return ErrForbidden }` — the query result is checked against the caller's scope before it is returned.\n\n**Injection sinks** — string-built SQL, `exec.Command(\"sh\",\"-c\",…)` \u002F `child_process.exec`, template `|safe`, `dangerouslySetInnerHTML`, `v-html`.\n- ❌ `db.Exec(fmt.Sprintf(\"SELECT * FROM tasks WHERE title = '%s'\", title))`\n- ✅ `db.Exec(\"SELECT * FROM tasks WHERE title = $1\", title)`\n\n**Path traversal, SSRF, open redirect** — a path or URL built from user input without an allowlist or a resolved-path check.\n- ❌ `http.ServeFile(w, r, filepath.Join(baseDir, r.URL.Query().Get(\"file\")))` — `..\u002F..\u002Fetc\u002Fpasswd` escapes `baseDir`.\n- ✅ resolve the joined path with `filepath.Clean`\u002F`EvalSymlinks` and reject anything outside `baseDir`.\n\n**Secrets** — in code, logs, error bodies, or **argv** (this repo's own rule: secrets never go on argv; a child process gets them via env, not a command-line flag).\n- ❌ `exec.Command(\"curl\", \"-H\", \"Authorization: Bearer \"+token, url)`\n- ✅ pass the token through an env var the child reads, never a flag.\n\n**Crypto** — `math\u002Frand`\u002F`Math.random` used for a token or session id; MD5\u002FSHA1 for a password hash.\n\n**CSRF \u002F CORS** — a cookie-authenticated state change with no CSRF check; `Access-Control-Allow-Origin: *` alongside credentialed requests.\n\n**Supply chain** — a new dependency: pinned in the lockfile, maintained, license-compatible, not a typo-squat of a popular name, and actually in scope (an out-of-scope list that forbids unrequested dependency changes still applies).\n\n**Exceptional conditions** — an error swallowed into a 200\u002Fsuccess response; auth that fails open (an unreachable check defaults to \"allowed\" instead of \"denied\").\n- ❌ `if err != nil { log.Error(err) }` then falls through and returns 200 anyway.\n- ✅ the error is propagated and mapped to the right status code.\n\n**LLM-specific** (any diff that calls a model or exposes a tool to one) — model output used directly as a shell command, a SQL fragment, or a URL; a tool callable on untrusted content (e.g. a webhook body) with no confirmation step. See OWASP Top 10 for LLM Applications, LLM01 Prompt Injection.\n\n## 5. Severity\n\n- **Critical** — exploitable without authentication, an auth bypass, an injection sink reachable by input, or a leaked secret.\n- **Critical when it reaches data, Important otherwise** — exploitable only with conditions (IDOR on a specific id, stored XSS, SSRF to an internal service).\n- **Minor** — defence-in-depth gaps (a check that is redundant with one already upstream).\n\n## 6. Before the Verdict\n\nState to yourself, not in the comment: which areas you could not verify and why (e.g. \"didn't trace the mobile client's handling of this field — out of this diff's repo\"). An unverifiable area is not a finding; it's a boundary of the review.\n\n## References (names and links only — OWASP content is CC BY-SA, not reproduced)\n\n[OWASP Top 10:2025](https:\u002F\u002Ftop10.owasp.org\u002F2025\u002F): A01 Broken Access Control · A03 Software Supply Chain Failures · A04 Cryptographic Failures · A05 Injection · A06 Insecure Design · A07 Authentication Failures · A08 Software\u002FData Integrity Failures · A09 Security Logging and Alerting Failures · A10 Mishandling of Exceptional Conditions. [OWASP Top 10 for LLM Applications](https:\u002F\u002Fgenai.owasp.org\u002F): LLM01 Prompt Injection.\n\n## Common Mistakes\n\n- Flagging a value from `os.Getenv` or a hardcoded constant as attacker-controlled.\n- Flagging React's `{value}` interpolation or an ORM's parameter binding as an injection risk — that is the escaping working.\n- A Critical for a low-tier diff (pure copy\u002FUI change) that has no reachable input at all.\n- Running the full checklist on a low-risk diff instead of just Secrets and Supply Chain.\n\n## Red Flags\n\n- A finding with no traced source for the \"attacker-controlled\" claim.\n- A new outbound call (`fetch_url`-equivalent, `http.Client`) with no mention of where the URL comes from.\n- A new dependency with no lockfile entry checked.\n- \"Might be exploitable\" with no file:line and no input trace — rewrite it with both, or drop it.\n","# Security Review\n\n## Overview\n\nSecurity is not a separate pass over the whole repo — it is one more lens on the diff (code_review) or the design (analysis) you are already reading. Report only what is reachable by an attacker; a theoretical issue with no path to it is noise that trains people to skip your findings.\n\n## 1. Risk Tier First\n\n- **High** — auth, payments, admin actions, file upload, outbound URL fetch, anything that calls an LLM with tool access. Run the full checklist below.\n- **Medium** — user data, external API calls. Run Injection, Authorization, Exceptional Conditions, Secrets.\n- **Low** — pure UI, utilities, pure config\u002Fcopy. Run Secrets and Supply Chain only.\n\n## 2. Map the Attack Surface (of the diff, not the repo)\n\nList, from the diff: every new input (params, headers, body, path segment, uploaded file, webhook payload, LLM output used downstream), every new or changed query, every auth\u002Fauthorization check, every outbound call, every secret touched.\n\n## 3. Report Only Attacker-Reachable Findings\n\nTrace the value to its source with `grep_code`\u002F`expand_symbol_context` before flagging it. **Not attacker-controlled:** config values, environment variables, constants, server-set values, test fixtures. **Not a finding:** framework auto-escaping doing its job (React `{x}`, an ORM's parameterized query) — that is the control working, not a gap.\n\n## 4. Checks\n\n**Authorization per new route** — does it carry the same middleware as its neighbours, and does the query filter by owner\u002Ftenant (IDOR)?\n- ❌ `func (h *Handler) GetInvoice(w, r) { id := r.PathValue(\"id\"); inv, _ := h.repo.Get(ctx, id); json.NewEncoder(w).Encode(inv) }` — any authenticated user reads any invoice by guessing an id.\n- ✅ `inv, err := h.repo.Get(ctx, id); if inv.OrgID != authctx.OrgID(ctx) { return ErrForbidden }` — the query result is checked against the caller's scope before it is returned.\n\n**Injection sinks** — string-built SQL, `exec.Command(\"sh\",\"-c\",…)` \u002F `child_process.exec`, template `|safe`, `dangerouslySetInnerHTML`, `v-html`.\n- ❌ `db.Exec(fmt.Sprintf(\"SELECT * FROM tasks WHERE title = '%s'\", title))`\n- ✅ `db.Exec(\"SELECT * FROM tasks WHERE title = $1\", title)`\n\n**Path traversal, SSRF, open redirect** — a path or URL built from user input without an allowlist or a resolved-path check.\n- ❌ `http.ServeFile(w, r, filepath.Join(baseDir, r.URL.Query().Get(\"file\")))` — `..\u002F..\u002Fetc\u002Fpasswd` escapes `baseDir`.\n- ✅ resolve the joined path with `filepath.Clean`\u002F`EvalSymlinks` and reject anything outside `baseDir`.\n\n**Secrets** — in code, logs, error bodies, or **argv** (this repo's own rule: secrets never go on argv; a child process gets them via env, not a command-line flag).\n- ❌ `exec.Command(\"curl\", \"-H\", \"Authorization: Bearer \"+token, url)`\n- ✅ pass the token through an env var the child reads, never a flag.\n\n**Crypto** — `math\u002Frand`\u002F`Math.random` used for a token or session id; MD5\u002FSHA1 for a password hash.\n\n**CSRF \u002F CORS** — a cookie-authenticated state change with no CSRF check; `Access-Control-Allow-Origin: *` alongside credentialed requests.\n\n**Supply chain** — a new dependency: pinned in the lockfile, maintained, license-compatible, not a typo-squat of a popular name, and actually in scope (an out-of-scope list that forbids unrequested dependency changes still applies).\n\n**Exceptional conditions** — an error swallowed into a 200\u002Fsuccess response; auth that fails open (an unreachable check defaults to \"allowed\" instead of \"denied\").\n- ❌ `if err != nil { log.Error(err) }` then falls through and returns 200 anyway.\n- ✅ the error is propagated and mapped to the right status code.\n\n**LLM-specific** (any diff that calls a model or exposes a tool to one) — model output used directly as a shell command, a SQL fragment, or a URL; a tool callable on untrusted content (e.g. a webhook body) with no confirmation step. See OWASP Top 10 for LLM Applications, LLM01 Prompt Injection.\n\n## 5. Severity\n\n- **Critical** — exploitable without authentication, an auth bypass, an injection sink reachable by input, or a leaked secret.\n- **Critical when it reaches data, Important otherwise** — exploitable only with conditions (IDOR on a specific id, stored XSS, SSRF to an internal service).\n- **Minor** — defence-in-depth gaps (a check that is redundant with one already upstream).\n\n## 6. Before the Verdict\n\nState to yourself, not in the comment: which areas you could not verify and why (e.g. \"didn't trace the mobile client's handling of this field — out of this diff's repo\"). An unverifiable area is not a finding; it's a boundary of the review.\n\n## References (names and links only — OWASP content is CC BY-SA, not reproduced)\n\n[OWASP Top 10:2025](https:\u002F\u002Ftop10.owasp.org\u002F2025\u002F): A01 Broken Access Control · A03 Software Supply Chain Failures · A04 Cryptographic Failures · A05 Injection · A06 Insecure Design · A07 Authentication Failures · A08 Software\u002FData Integrity Failures · A09 Security Logging and Alerting Failures · A10 Mishandling of Exceptional Conditions. [OWASP Top 10 for LLM Applications](https:\u002F\u002Fgenai.owasp.org\u002F): LLM01 Prompt Injection.\n\n## Common Mistakes\n\n- Flagging a value from `os.Getenv` or a hardcoded constant as attacker-controlled.\n- Flagging React's `{value}` interpolation or an ORM's parameter binding as an injection risk — that is the escaping working.\n- A Critical for a low-tier diff (pure copy\u002FUI change) that has no reachable input at all.\n- Running the full checklist on a low-risk diff instead of just Secrets and Supply Chain.\n\n## Red Flags\n\n- A finding with no traced source for the \"attacker-controlled\" claim.\n- A new outbound call (`fetch_url`-equivalent, `http.Client`) with no mention of where the URL comes from.\n- A new dependency with no lockfile entry checked.\n- \"Might be exploitable\" with no file:line and no input trace — rewrite it with both, or drop it.\n",{"name":5,"source":24,"category":25,"description":7},"getsentry\u002Fskills find-bugs (Apache-2.0), anthropics\u002Fclaude-plugins-official (Apache-2.0), github\u002Fawesome-copilot se-security-reviewer (MIT), adapted; OWASP category names linked only","quality","main","910394a0b6db9fc8c9a8f36328ec421d3ebd8b38","catalog\u002Fagents\u002Fsystem-architect\u002Fskills\u002Fsecurity-review",18,"https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper","https:\u002F\u002Ftasktrooper.ai","https:\u002F\u002Fgithub.com\u002Fmakifbaysal","Senior Software Developer","2026-11-15 04:50:29",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add makifbaysal\u002Ftasktrooper --skill security-review",{"tool":41,"command":42},"bunx","bunx skills add makifbaysal\u002Ftasktrooper --skill security-review",{"tool":44,"command":45},"pnpm","pnpm dlx skills add makifbaysal\u002Ftasktrooper --skill security-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fsystem-architect\u002Fskills\u002Fsecurity-review\u002FSKILL.md",true,[],[50,56,63,70,77,84],{"skillNo":51,"name":52,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7CSVEPQW6J6TD6CS2T5FPNZ","visual-craft","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fvisual-craft\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7CSVAQG91ETHQ0HBNZDG5FR","ux-copy","Use when you write any words a user reads in a mockup or a hand-off - content language and voice, buttons, labels, errors, empty states, confirmations, numbers and dates, and the longest-string check","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fux-copy\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7CSV6H0J38659NDXHJQ8396","screen-mockup-html","Use when you draw screens as the design task's HTML mockup - ONE canvas document holding every screen and every variant side by side, the sanitizer-safe recipe, phone and wide frames, the states grid, static control states, and the loopback self-check with screenshots at 375, 768 and 1440 attached to the task","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fscreen-mockup-html\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CSV3JFRF3BM3XK52M7YEYR","performance-awareness","How the performance score moves for your role. Use when the score context shows a declining trend, or before handing off work you have not self-checked against every criterion.","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fperformance-awareness\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CSTZDH00YRF5SCT7BRT9QD","design-variants","Use when a screen design needs variants - how many, variants as side-by-side rows on the one canvas, what makes two variants genuinely different, recommending one, how the human's choice is read, and narrowing to the chosen one in revision","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-variants\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7CSTV6P3SM3PAE28DB0RF77","design-system-authoring","Use when you derive, change or extend a design system - where tokens live per stack, the DTCG token tree, role-based names for both themes, base vs layer vs drift, the DESIGN.md section order, the inventory format, the contrast check and the lint every proposal returns","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-system-authoring\u002FSKILL.md",[],[]]