[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75CKB8YZA8FYFSCYR4S1V34":3,"skill-same:01M75CKB8YZA8FYFSCYR4S1V34":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M75CKB8YZA8FYFSCYR4S1V34","cosmos-vulnerability-scanner",null,"Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities — chain halts, fund loss, state divergence. 25 core + 16 IBC + 10 EVM + 3 CosmWasm patterns. Use when auditing custom x\u002F modules, reviewing IBC integrations, or assessing pre-launch chain security. Updated for SDK v0.53.x.","agisota\u002Fold-one","agisota","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121413592?v=4","01M75B4BRNT67EC1NDRT8QZEP2","01M75B4BS7QR9VP580MSCPTS3X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: cosmos-vulnerability-scanner\ndescription: \"Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities — chain halts, fund loss, state divergence. 25 core + 16 IBC + 10 EVM + 3 CosmWasm patterns. Use when auditing custom x\u002F modules, reviewing IBC integrations, or assessing pre-launch chain security. Updated for SDK v0.53.x.\"\n---\n\n# Cosmos Vulnerability Scanner\n\n## Purpose\n\nScan Cosmos SDK modules and CosmWasm contracts for vulnerabilities that cause chain halts, consensus failures, or fund loss. Spawns parallel scanning agents — each specializing in a vulnerability category — that return findings to the main skill, which then writes them as individual markdown files to an output directory.\n\n**Output directory**: defaults to `.bughunt_cosmos\u002F`. If the user specifies a different directory in their prompt, use that instead.\n\n## When to Use\n\n- Auditing Cosmos SDK modules (custom `x\u002F` modules)\n- Reviewing CosmWasm smart contracts\n- Pre-launch security assessment of Cosmos chains\n- Investigating chain halt incidents\n\n## When NOT to Use\n\n- Pure Solidity\u002FEVM audits without Cosmos SDK — use Solidity-specific tools\n- CometBFT consensus engine internals — this covers SDK modules, not the consensus layer itself\n- General Go code review with no blockchain context\n- Cosmos SDK application logic that is not consensus-critical (e.g., CLI commands, REST endpoints)\n- CosmWasm contract-only audits on chains without custom SDK modules — use the CosmWasm checklist items alone\n\n## Essential Principles\n\n1. **Consensus path is king** — A bug only matters for chain halt\u002Ffund loss if it's on the consensus-critical execution path (BeginBlock, EndBlock, FinalizeBlock, msg_server handlers, AnteHandler). Always verify a finding is reachable from consensus before reporting it.\n2. **State divergence = chain halt** — Any non-determinism that causes validators to compute different state roots will halt the chain. This is the highest-severity class because it affects all validators simultaneously.\n3. **Check the version** — Cosmos SDK has breaking changes across major versions (v0.47 removed GetSigners, v0.50 added ABCI 2.0, v0.53 deprecated ValidateBasic). Always check `go.mod` versions before applying patterns.\n4. **False positives waste audit time** — A map iteration in a CLI command is not a consensus bug. A panic in a query handler does not halt the chain. Verify the execution context before flagging.\n5. **Cross-module interactions are where bugs hide** — The most severe findings (IBC reentrancy, EVM\u002FCosmos state desync, authz escalation) involve interactions between modules, not bugs within a single module.\n\n## Scanning Workflow\n\n### Phase 1: Discovery (synchronous)\n\n**Entry**: Target codebase path provided by user. Codebase contains Go source (e.g., `x\u002F` modules, `go.mod`) or Rust contracts with `cosmwasm_std`.\n\nRun a **synchronous subagent** (Agent tool) with the full contents of [DISCOVERY.md](resources\u002FDISCOVERY.md) as its prompt. The agent must:\n\n1. Follow the Discovery workflow to explore the target codebase\n2. Return the full CLAUDE.md content (the technical inventory and threat model) in its response\n3. Return a structured summary with exactly these fields:\n\n```\nPLATFORM: pure-cosmos | evm | wasm        (pick one; if multiple, comma-separated)\nIBC_ENABLED: true | false\nSDK_VERSION: \u003Cversion from go.mod>\nIBC_GO_VERSION: \u003Cversion from go.mod, or \"n\u002Fa\">\nCUSTOM_MODULES: \u003Ccomma-separated list of x\u002F* modules>\n```\n\nAfter the subagent returns, **you** (the main skill) Write the CLAUDE.md to the target repo root. Save its path and the discovery values — these feed into Phase 2.\n\n**Exit**: CLAUDE.md written by main skill. PLATFORM, IBC_ENABLED, SDK_VERSION, IBC_GO_VERSION, and CUSTOM_MODULES captured.\n\n### Phase 2: Parallel Vulnerability Scan\n\nSpawn scanning agents **in a single message** for maximum parallelism. Use the Agent Prompt Template below, filling in the reference file for each agent. Subagents only need read access (Grep, Glob, Read) — they return findings in their response and the main skill writes the files.\n\n**Always spawn these 3 agents:**\n\n| Agent Name | Reference File | Scope |\n|------------|---------------|-------|\n| `core-scanner` | `VULNERABILITY_PATTERNS.md` | §1-9: non-determinism, ABCI, signers, validation, handlers, ante security |\n| `state-scanner` | `STATE_VULNERABILITY_PATTERNS.md` | §11-23: bookkeeping, bank, pagination, events, tx replay, governance, arithmetic, encoding, deprecated modules |\n| `advanced-scanner` | `ADVANCED_VULNERABILITY_PATTERNS.md` | §24-27: storage keys, consensus validation, circuit breaker, crypto |\n\n**Spawn conditionally (in the same parallel message):**\n\n| Agent Name | Condition | Reference File |\n|------------|-----------|---------------|\n| `evm-scanner` | PLATFORM includes `evm` | `EVM_VULNERABILITY_PATTERNS.md` |\n| `ibc-scanner` | IBC_ENABLED is `true` | `IBC_VULNERABILITY_PATTERNS.md` |\n| `cosmwasm-scanner` | PLATFORM includes `wasm` | `COSMWASM_VULNERABILITY_PATTERNS.md` |\n\n#### Agent Prompt Template\n\nConstruct each agent's prompt by replacing `{REFERENCE_FILE_PATH}` with the full path to the reference file (under `{baseDir}\u002Fresources\u002F`) and `{CLAUDE_MD_PATH}` with the path to the CLAUDE.md written in Phase 1:\n\n~~~\nPerform a very thorough security scan of a Cosmos SDK codebase for specific vulnerability patterns.\n\nCONTEXT:\nRead {CLAUDE_MD_PATH} for codebase context (SDK version, modules, threat model, key files).\n\nPATTERNS:\nRead {REFERENCE_FILE_PATH} — it contains numbered vulnerability patterns. For EACH pattern:\n1. Read the detection patterns and \"What to Check\" items\n2. Use Grep and Glob to search the target codebase for each pattern\n3. When a match is found, Read surrounding code to verify it's on a consensus-critical path (BeginBlock, EndBlock, FinalizeBlock, msg_server handlers, AnteHandler)\n4. Classify severity per the guidelines below\n\nRULES:\n- Consensus path only: Only flag code reachable from consensus-critical execution. CLI\u002Fquery\u002Ftest code is NOT a finding.\n- Check SDK version in go.mod before applying patterns (v0.47 removed GetSigners, v0.50 added ABCI 2.0, v0.53 deprecated ValidateBasic).\n- Always use the Grep tool for searches, not bash grep. The reference file contains search patterns — use them directly with the Grep tool.\n- Ignore cross-references to other resource files (e.g., links to IBC or COSMWASM patterns). Those patterns are covered by other scanning agents.\n- Reject these rationalizations:\n  - \"ValidateBasic catches this\" — deprecated and facultative since SDK v0.53\n  - \"Behind governance, so safe\" — governance proposals can be malicious\n  - \"IBC counterparty is trusted\" — any chain can open a channel\n  - \"Panic can't happen, input is validated\" — trace the full call chain\n  - \"Rounding error is only a few tokens\" — compounds over time, can be looped\n  - \"EVM precompile handles rollback\" — many have incomplete rollback\n\nSEVERITY:\n- Critical (fund loss): signer mismatch, broken bookkeeping, AnteHandler bypass, bank keeper misuse, IBC token inflation, EVM\u002FCosmos desync, Merkle proof forgery, arithmetic overflow\n- High (chain halt): non-determinism, ABCI panics, slow ABCI, non-deterministic IBC acks, consensus gaps, CacheContext event leak\n- Medium (DoS): unbounded pagination, tx replay, missing validation, governance spam, rate limiting, circuit breaker bypass, storage key collisions\n- Low (logic): rounding errors, stub handlers, event override, module ordering\n\nOUTPUT — RETURN FORMAT:\nDo NOT write any files. Return ALL findings and the summary in your response.\n\nFor each pattern, return one of:\n  §NUM PATTERN_NAME: Not applicable — [one-line reason]\n  §NUM PATTERN_NAME: FINDING (followed by the finding block below)\n\nFor each finding, include the full content using this template:\n\nFINDING_FILE: {SEVERITY}-s{SECTION_NUM}-{kebab-description}.md\n## [SEVERITY] Title\n**Location**: `file:line`\n**Description**: What the bug is and why it matters\n**Vulnerable Code**: [snippet]\n**Attack Scenario**: [numbered steps]\n**Recommendation**: How to fix\n**References**: [links to relevant advisories or building-secure-contracts]\n\nYou MUST report on ALL patterns in the reference file — do not skip any.\n~~~\n\n**Exit**: All scanning agents returned. Each reported on every pattern in their reference file.\n\n### Phase 3: Write Findings\n\nAfter all scanning agents return, write finding files to the output directory (default `.bughunt_cosmos\u002F`):\n\n1. Parse each agent's response for `FINDING_FILE:` blocks\n2. For each finding, Write the content to `{OUTPUT_DIR}\u002F{filename}` using the filename from `FINDING_FILE:`\n3. Create the output directory first if it doesn't exist\n\n### Phase 4: Verify Completeness\n\nAfter writing all findings, verify every pattern was assessed:\n\n1. Collect the summary lines (§NUM entries) returned by each agent\n2. Check pattern counts against expected totals:\n   - `core-scanner`: 8 patterns (§1-9, excluding §8 legacy-only)\n   - `state-scanner`: 13 patterns (§11-23)\n   - `advanced-scanner`: 4 patterns (§24-27)\n   - `evm-scanner` (if spawned): 10 patterns (§1-10)\n   - `ibc-scanner` (if spawned): 16 patterns (§1-16)\n   - `cosmwasm-scanner` (if spawned): 3 patterns (§1-3)\n3. If any pattern is missing from a summary, flag it and re-prompt that agent\n4. List all finding files written to the output directory with a `Glob` for `*.md`\n\n**Exit**: All patterns accounted for. Finding files listed for the user.\n\n---\n\n## Success Criteria\n\n- [ ] Discovery CLAUDE.md written with complete technical inventory and threat model\n- [ ] All scanning agents completed and reported on every pattern in their reference file\n- [ ] Pattern counts verified against expected totals (no patterns skipped)\n- [ ] All findings written to output directory as individual markdown files\n- [ ] Each finding file includes: severity, location, vulnerable code, attack scenario, recommendation\n\n---\n\n## Resources\n\n- **Discovery & CLAUDE.md**: [DISCOVERY.md](resources\u002FDISCOVERY.md)\n- **Core patterns (§1-9)**: [VULNERABILITY_PATTERNS.md](resources\u002FVULNERABILITY_PATTERNS.md)\n- **State & module patterns (§11-23)**: [STATE_VULNERABILITY_PATTERNS.md](resources\u002FSTATE_VULNERABILITY_PATTERNS.md)\n- **Advanced patterns (§24-27)**: [ADVANCED_VULNERABILITY_PATTERNS.md](resources\u002FADVANCED_VULNERABILITY_PATTERNS.md)\n- **IBC vulnerabilities**: [IBC_VULNERABILITY_PATTERNS.md](resources\u002FIBC_VULNERABILITY_PATTERNS.md)\n- **CosmWasm vulnerabilities**: [COSMWASM_VULNERABILITY_PATTERNS.md](resources\u002FCOSMWASM_VULNERABILITY_PATTERNS.md)\n- **EVM vulnerabilities**: [EVM_VULNERABILITY_PATTERNS.md](resources\u002FEVM_VULNERABILITY_PATTERNS.md)\n- **Building Secure Contracts**: `building-secure-contracts\u002Fnot-so-smart-contracts\u002Fcosmos\u002F`\n- **Cosmos SDK Docs**: https:\u002F\u002Fdocs.cosmos.network\u002F\n- **CodeQL for Cosmos SDK**: https:\u002F\u002Fgithub.com\u002Fcrypto-com\u002Fcosmos-sdk-codeql\n","# Cosmos Vulnerability Scanner\n\n## Purpose\n\nScan Cosmos SDK modules and CosmWasm contracts for vulnerabilities that cause chain halts, consensus failures, or fund loss. Spawns parallel scanning agents — each specializing in a vulnerability category — that return findings to the main skill, which then writes them as individual markdown files to an output directory.\n\n**Output directory**: defaults to `.bughunt_cosmos\u002F`. If the user specifies a different directory in their prompt, use that instead.\n\n## When to Use\n\n- Auditing Cosmos SDK modules (custom `x\u002F` modules)\n- Reviewing CosmWasm smart contracts\n- Pre-launch security assessment of Cosmos chains\n- Investigating chain halt incidents\n\n## When NOT to Use\n\n- Pure Solidity\u002FEVM audits without Cosmos SDK — use Solidity-specific tools\n- CometBFT consensus engine internals — this covers SDK modules, not the consensus layer itself\n- General Go code review with no blockchain context\n- Cosmos SDK application logic that is not consensus-critical (e.g., CLI commands, REST endpoints)\n- CosmWasm contract-only audits on chains without custom SDK modules — use the CosmWasm checklist items alone\n\n## Essential Principles\n\n1. **Consensus path is king** — A bug only matters for chain halt\u002Ffund loss if it's on the consensus-critical execution path (BeginBlock, EndBlock, FinalizeBlock, msg_server handlers, AnteHandler). Always verify a finding is reachable from consensus before reporting it.\n2. **State divergence = chain halt** — Any non-determinism that causes validators to compute different state roots will halt the chain. This is the highest-severity class because it affects all validators simultaneously.\n3. **Check the version** — Cosmos SDK has breaking changes across major versions (v0.47 removed GetSigners, v0.50 added ABCI 2.0, v0.53 deprecated ValidateBasic). Always check `go.mod` versions before applying patterns.\n4. **False positives waste audit time** — A map iteration in a CLI command is not a consensus bug. A panic in a query handler does not halt the chain. Verify the execution context before flagging.\n5. **Cross-module interactions are where bugs hide** — The most severe findings (IBC reentrancy, EVM\u002FCosmos state desync, authz escalation) involve interactions between modules, not bugs within a single module.\n\n## Scanning Workflow\n\n### Phase 1: Discovery (synchronous)\n\n**Entry**: Target codebase path provided by user. Codebase contains Go source (e.g., `x\u002F` modules, `go.mod`) or Rust contracts with `cosmwasm_std`.\n\nRun a **synchronous subagent** (Agent tool) with the full contents of [DISCOVERY.md](resources\u002FDISCOVERY.md) as its prompt. The agent must:\n\n1. Follow the Discovery workflow to explore the target codebase\n2. Return the full CLAUDE.md content (the technical inventory and threat model) in its response\n3. Return a structured summary with exactly these fields:\n\n```\nPLATFORM: pure-cosmos | evm | wasm        (pick one; if multiple, comma-separated)\nIBC_ENABLED: true | false\nSDK_VERSION: \u003Cversion from go.mod>\nIBC_GO_VERSION: \u003Cversion from go.mod, or \"n\u002Fa\">\nCUSTOM_MODULES: \u003Ccomma-separated list of x\u002F* modules>\n```\n\nAfter the subagent returns, **you** (the main skill) Write the CLAUDE.md to the target repo root. Save its path and the discovery values — these feed into Phase 2.\n\n**Exit**: CLAUDE.md written by main skill. PLATFORM, IBC_ENABLED, SDK_VERSION, IBC_GO_VERSION, and CUSTOM_MODULES captured.\n\n### Phase 2: Parallel Vulnerability Scan\n\nSpawn scanning agents **in a single message** for maximum parallelism. Use the Agent Prompt Template below, filling in the reference file for each agent. Subagents only need read access (Grep, Glob, Read) — they return findings in their response and the main skill writes the files.\n\n**Always spawn these 3 agents:**\n\n| Agent Name | Reference File | Scope |\n|------------|---------------|-------|\n| `core-scanner` | `VULNERABILITY_PATTERNS.md` | §1-9: non-determinism, ABCI, signers, validation, handlers, ante security |\n| `state-scanner` | `STATE_VULNERABILITY_PATTERNS.md` | §11-23: bookkeeping, bank, pagination, events, tx replay, governance, arithmetic, encoding, deprecated modules |\n| `advanced-scanner` | `ADVANCED_VULNERABILITY_PATTERNS.md` | §24-27: storage keys, consensus validation, circuit breaker, crypto |\n\n**Spawn conditionally (in the same parallel message):**\n\n| Agent Name | Condition | Reference File |\n|------------|-----------|---------------|\n| `evm-scanner` | PLATFORM includes `evm` | `EVM_VULNERABILITY_PATTERNS.md` |\n| `ibc-scanner` | IBC_ENABLED is `true` | `IBC_VULNERABILITY_PATTERNS.md` |\n| `cosmwasm-scanner` | PLATFORM includes `wasm` | `COSMWASM_VULNERABILITY_PATTERNS.md` |\n\n#### Agent Prompt Template\n\nConstruct each agent's prompt by replacing `{REFERENCE_FILE_PATH}` with the full path to the reference file (under `{baseDir}\u002Fresources\u002F`) and `{CLAUDE_MD_PATH}` with the path to the CLAUDE.md written in Phase 1:\n\n~~~\nPerform a very thorough security scan of a Cosmos SDK codebase for specific vulnerability patterns.\n\nCONTEXT:\nRead {CLAUDE_MD_PATH} for codebase context (SDK version, modules, threat model, key files).\n\nPATTERNS:\nRead {REFERENCE_FILE_PATH} — it contains numbered vulnerability patterns. For EACH pattern:\n1. Read the detection patterns and \"What to Check\" items\n2. Use Grep and Glob to search the target codebase for each pattern\n3. When a match is found, Read surrounding code to verify it's on a consensus-critical path (BeginBlock, EndBlock, FinalizeBlock, msg_server handlers, AnteHandler)\n4. Classify severity per the guidelines below\n\nRULES:\n- Consensus path only: Only flag code reachable from consensus-critical execution. CLI\u002Fquery\u002Ftest code is NOT a finding.\n- Check SDK version in go.mod before applying patterns (v0.47 removed GetSigners, v0.50 added ABCI 2.0, v0.53 deprecated ValidateBasic).\n- Always use the Grep tool for searches, not bash grep. The reference file contains search patterns — use them directly with the Grep tool.\n- Ignore cross-references to other resource files (e.g., links to IBC or COSMWASM patterns). Those patterns are covered by other scanning agents.\n- Reject these rationalizations:\n  - \"ValidateBasic catches this\" — deprecated and facultative since SDK v0.53\n  - \"Behind governance, so safe\" — governance proposals can be malicious\n  - \"IBC counterparty is trusted\" — any chain can open a channel\n  - \"Panic can't happen, input is validated\" — trace the full call chain\n  - \"Rounding error is only a few tokens\" — compounds over time, can be looped\n  - \"EVM precompile handles rollback\" — many have incomplete rollback\n\nSEVERITY:\n- Critical (fund loss): signer mismatch, broken bookkeeping, AnteHandler bypass, bank keeper misuse, IBC token inflation, EVM\u002FCosmos desync, Merkle proof forgery, arithmetic overflow\n- High (chain halt): non-determinism, ABCI panics, slow ABCI, non-deterministic IBC acks, consensus gaps, CacheContext event leak\n- Medium (DoS): unbounded pagination, tx replay, missing validation, governance spam, rate limiting, circuit breaker bypass, storage key collisions\n- Low (logic): rounding errors, stub handlers, event override, module ordering\n\nOUTPUT — RETURN FORMAT:\nDo NOT write any files. Return ALL findings and the summary in your response.\n\nFor each pattern, return one of:\n  §NUM PATTERN_NAME: Not applicable — [one-line reason]\n  §NUM PATTERN_NAME: FINDING (followed by the finding block below)\n\nFor each finding, include the full content using this template:\n\nFINDING_FILE: {SEVERITY}-s{SECTION_NUM}-{kebab-description}.md\n## [SEVERITY] Title\n**Location**: `file:line`\n**Description**: What the bug is and why it matters\n**Vulnerable Code**: [snippet]\n**Attack Scenario**: [numbered steps]\n**Recommendation**: How to fix\n**References**: [links to relevant advisories or building-secure-contracts]\n\nYou MUST report on ALL patterns in the reference file — do not skip any.\n~~~\n\n**Exit**: All scanning agents returned. Each reported on every pattern in their reference file.\n\n### Phase 3: Write Findings\n\nAfter all scanning agents return, write finding files to the output directory (default `.bughunt_cosmos\u002F`):\n\n1. Parse each agent's response for `FINDING_FILE:` blocks\n2. For each finding, Write the content to `{OUTPUT_DIR}\u002F{filename}` using the filename from `FINDING_FILE:`\n3. Create the output directory first if it doesn't exist\n\n### Phase 4: Verify Completeness\n\nAfter writing all findings, verify every pattern was assessed:\n\n1. Collect the summary lines (§NUM entries) returned by each agent\n2. Check pattern counts against expected totals:\n   - `core-scanner`: 8 patterns (§1-9, excluding §8 legacy-only)\n   - `state-scanner`: 13 patterns (§11-23)\n   - `advanced-scanner`: 4 patterns (§24-27)\n   - `evm-scanner` (if spawned): 10 patterns (§1-10)\n   - `ibc-scanner` (if spawned): 16 patterns (§1-16)\n   - `cosmwasm-scanner` (if spawned): 3 patterns (§1-3)\n3. If any pattern is missing from a summary, flag it and re-prompt that agent\n4. List all finding files written to the output directory with a `Glob` for `*.md`\n\n**Exit**: All patterns accounted for. Finding files listed for the user.\n\n---\n\n## Success Criteria\n\n- [ ] Discovery CLAUDE.md written with complete technical inventory and threat model\n- [ ] All scanning agents completed and reported on every pattern in their reference file\n- [ ] Pattern counts verified against expected totals (no patterns skipped)\n- [ ] All findings written to output directory as individual markdown files\n- [ ] Each finding file includes: severity, location, vulnerable code, attack scenario, recommendation\n\n---\n\n## Resources\n\n- **Discovery & CLAUDE.md**: [DISCOVERY.md](resources\u002FDISCOVERY.md)\n- **Core patterns (§1-9)**: [VULNERABILITY_PATTERNS.md](resources\u002FVULNERABILITY_PATTERNS.md)\n- **State & module patterns (§11-23)**: [STATE_VULNERABILITY_PATTERNS.md](resources\u002FSTATE_VULNERABILITY_PATTERNS.md)\n- **Advanced patterns (§24-27)**: [ADVANCED_VULNERABILITY_PATTERNS.md](resources\u002FADVANCED_VULNERABILITY_PATTERNS.md)\n- **IBC vulnerabilities**: [IBC_VULNERABILITY_PATTERNS.md](resources\u002FIBC_VULNERABILITY_PATTERNS.md)\n- **CosmWasm vulnerabilities**: [COSMWASM_VULNERABILITY_PATTERNS.md](resources\u002FCOSMWASM_VULNERABILITY_PATTERNS.md)\n- **EVM vulnerabilities**: [EVM_VULNERABILITY_PATTERNS.md](resources\u002FEVM_VULNERABILITY_PATTERNS.md)\n- **Building Secure Contracts**: `building-secure-contracts\u002Fnot-so-smart-contracts\u002Fcosmos\u002F`\n- **Cosmos SDK Docs**: https:\u002F\u002Fdocs.cosmos.network\u002F\n- **CodeQL for Cosmos SDK**: https:\u002F\u002Fgithub.com\u002Fcrypto-com\u002Fcosmos-sdk-codeql\n",{"name":5,"description":7},"main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Fcosmos-vulnerability-scanner",1,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one","https:\u002F\u002Fagisota.github.io\u002Fold-one\u002F","https:\u002F\u002Fgithub.com\u002Fagisota","pzd.world","2026-07-04 22:32:06",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add agisota\u002Fold-one --skill cosmos-vulnerability-scanner",{"tool":38,"command":39},"bunx","bunx skills add agisota\u002Fold-one --skill cosmos-vulnerability-scanner",{"tool":41,"command":42},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill cosmos-vulnerability-scanner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002FSKILL.md",true,[46,52,56,60,64,68,72,76],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"CHANGELOG.md","REFERENCE","参考文档",12950,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002FCHANGELOG.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"resources\u002FADVANCED_VULNERABILITY_PATTERNS.md",12800,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002Fresources\u002FADVANCED_VULNERABILITY_PATTERNS.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"resources\u002FCOSMWASM_VULNERABILITY_PATTERNS.md",7643,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002Fresources\u002FCOSMWASM_VULNERABILITY_PATTERNS.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"resources\u002FDISCOVERY.md",3018,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002Fresources\u002FDISCOVERY.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"resources\u002FEVM_VULNERABILITY_PATTERNS.md",18442,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002Fresources\u002FEVM_VULNERABILITY_PATTERNS.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"resources\u002FIBC_VULNERABILITY_PATTERNS.md",28119,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002Fresources\u002FIBC_VULNERABILITY_PATTERNS.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"resources\u002FSTATE_VULNERABILITY_PATTERNS.md",29890,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002Fresources\u002FSTATE_VULNERABILITY_PATTERNS.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"resources\u002FVULNERABILITY_PATTERNS.md",27033,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcosmos-vulnerability-scanner\u002Fresources\u002FVULNERABILITY_PATTERNS.md",[81,88,95,104,111,118],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M75KRGZWQWE9JDBS6RX42NWV","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M75KRCZHKE0ZYAQFFYHS0YNP","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":99,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M75KR94KYQ30DTE1P9WNDAE0","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M75KR3H13YJ9QHMD49818FA1","yara-rule-authoring","Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyara-rule-authoring\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M75KQMPY8A4Y8XTDD2DT0M9T","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":18},"01M75KQHNZ0ANZNJGZY6M8MDAK","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]