โณ This skill is pending AI review.
Scores will appear once the review pipeline completes.
agentsec
>
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Run one command to audit every skill your AI agent uses against the OWASP Agentic Skills Top 10. agentsec is agent-platform agnostic โ it supports Claude Code, OpenClaw / ClawHub, Codex / skills.sh, Hermes (Nous Research), and generic project-local skill directories.
Quick Start
npx agentsec
No flags needed. agentsec walks every default skills directory on your machine โ grouped by platform โ plus any ./skills folder in the current project (up to two levels deep).
Use as an Agent Skill
agentsec is published as an OpenClaw skill on ClawHub. Agents that support ClawHub can install it directly:
npx clawhub install markeljan/agentsec
Then ask the agent to audit your skills โ it'll invoke npx agentsec and surface the findings.
Example Output
โ Found 7 skills
โน Scanned 5 locations across Claude Code, OpenClaw, Codex / skills.sh, Hermes, Other
Claude Code
~/.claude/skills (3 skills)
OpenClaw
~/.openclaw/workspace/skills (1 skill)
Codex / skills.sh
~/.agents/skills (1 skill)
Hermes
~/.hermes/skills (1 skill)
Other
./skills (1 skill)
Scanning Skills
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Claude Code (3 skills)
โ fetch-data v1.0.0 D (42)
โ deploy-helper v2.3.0 C (68)
โ code-review v1.1.0 A (95)
OpenClaw (1 skill)
โ summarize-docs v0.9.0 A (91)
Codex / skills.sh (1 skill)
โ db-migrate v1.4.2 B (78)
Hermes (1 skill)
โ research-assistant v0.3.1 B (82)
Other (1 skill)
โ lint-fix v2.0.0 A (93)
7 skills scanned โข avg score 79 โข 5 certified
Findings: 2 critical, 1 high, 2 medium
โ WARN 3 high/critical finding(s) detected
Run with --verbose for detailed findings and recommendations.
Auto-discovery
Running npx agentsec with no arguments scans every default skills directory for the agent platforms agentsec supports, then walks the current working directory for a generic skills/ folder:
| Platform | Paths scanned |
|---|---|
| Claude Code | ~/.claude/skills, ./.claude/skills, ~/.claude/plugins/*/skills/*, ~/.claude/commands, ./.claude/commands (legacy) |
| OpenClaw / ClawHub | ~/.openclaw/workspace/skills, ~/.openclaw/workspace-*/skills (profiles via OPENCLAW_PROFILE), ~/.openclaw/skills |
| Codex / skills.sh | ~/.agents/skills, ./.agents/skills, ../.agents/skills, /etc/codex/skills |
| Hermes | ~/.hermes/skills, ~/.hermes/skills/* (bundled categories), ./.hermes/skills |
| Other (generic) | Any skills/ directory found within the current working directory, up to two levels deep |
Discovered skills are grouped by platform in the output so you can see at a glance where each skill came from. Pass --path <dir> to audit a specific directory instead, or --platform <claude\|openclaw\|codex\|hermes> to narrow to one platform.
CLI Commands
# Scan current directory (auto-detects agent skills)
npx agentsec
# Show detailed findings, score breakdowns, and recommendations
npx agentsec --verbose
# Scan a specific path
npx agentsec scan --path ./my-project
# Apply a policy preset
npx agentsec audit --policy strict
npx agentsec audit --policy enterprise
# Output formats
npx agentsec --format json --output audit.json
npx agentsec --format sarif --output audit.sarif
npx agentsec --format html --output report.html
# Generate a report from a saved audit
npx agentsec report audit.json --format html --output report.html
See examples/ for full report samples in HTML, JSON, SARIF, and text formats.
OWASP Agentic Skills Top 10
Every scan checks for all 10 risk categories:
| ID | Risk | What We Detect |
|---|---|---|
| AST01 | Malicious Skills | Dangerous code patterns, hardcoded secrets, unsafe deserialization, known-malicious signatures |
| AST02 | Supply Chain Compromise | Dependency provenance, transparency log gaps |
| AST03 | Over-Privileged Skills | Excessive permission grants, over-broad allowed-tools, least-privilege violations |
| AST04 | Insecure Metadata | Schema validation failures, metadata integrity issues |
| AST05 | Untrusted External Instructions | Indirect prompt injection, covert-action & exfiltration directives, dynamic load-time execution in skill content |
| AST06 | Weak Isolation | Missing sandboxing, container misconfigurations |
| AST07 | Update Drift | Unpinned versions, stale dependencies, hash mismatches |
| AST08 | Poor Scanning | Coverage gaps, incomplete scanning pipelines |
| AST09 | No Governance | Missing audit logs, absent policy enforcement |
| AST10 | Cross-Platform Reuse | Platform-specific validation gaps, portability issues |
Web3 Annex (AST-W01โW12)
Skills that touch chain (signing, RPC, EIP-7702 delegation, MCP chain-tools, etc.) are auto-detected and audited against 12 additional rules from the @agentsec/web3 annex. Force the rule pack on for cross-team CI consistency:
npx agentsec --profile web3
| ID | Risk |
|---|---|
| AST-W01 | Unbounded Signing Authority |
| AST-W02 | Implicit Permit / Permit2 Signature Capture |
| AST-W03 | Delegation Hijack via EIP-7702 |
| AST-W04 | Blind / Opaque Signing |
| AST-W05 | RPC Substitution / Mempool Leakage |
| AST-W06 | Unverified Contract Call Targets |
| AST-W07 | Cross-Chain / Bridge Action Replay |
| AST-W08 | MCP Chain-Tool Drift / Capability Smuggling |
| AST-W09 | Session-Key Permission-Caveat Erosion |
| AST-W10 | Slippage / Oracle Manipulation by Agent Loop |
| AST-W11 | Key Material in Agent Memory / Logs |
| AST-W12 | No On-Chain Action Audit / Kill-Switch |
Findings carry thei
// HOW IT'S BUILT
// FILES
3 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
skills/agentsec/SKILL.md11 KBf1c773307b39upstream โ
--- name: agentsec description: > Audit AI agent skills for security vulnerabilities. Use when scanning installed skills against the OWASP Agentic Skills Top 10, checking skills before running them, gating CI/CD on skill safety, or generating audit reports (text, JSON, SARIF, HTML) for stakeholders. version: 0.4.0 license: MIT homepage: https://agentsec.sh author: semiotic-ai permissions: - filesystem:read metadata: agentsec: profile: meta openclaw: emoji: "๐ก๏ธ" homepage: https://agentsec.sh requires: anyBins: - agentsec - npx - bunx install: - kind: node package: agentsec bins: - agentsec label: Install agentsec (npm) --- # agentsec `agentsec` is a security auditing CLI for AI agent skills. It scans every skill installed in a project against the OWASP Agentic Skills Top 10 and reports vulnerabilities, misconfigurations, and governance gaps. ## When to Use Use `agentsec` when the user asks to: - Audit, scan, or check agent skills for security issues - Verify installed skills are safe before running them - Check OWASP compliance of an agent setup - Gate a CI/CD pipeline on skill security - Generate a security report for stakeholders ## Quick Start The fastest path to a result โ no install, no flags: ```bash npx agentsec ``` This scans every default skills directory on the machine โ grouped by platform โ plus any `./skills` folder in the current project (up to two levels deep), and audits each installed skill against the OWASP Agentic Skills Top 10. Always try this first. ### Auto-discovery locations agentsec is agent-platform agnostic โ every platform listed below ships skills in the [agentskills.io](https://agentskills.io/specification) `SKILL.md` format and is auto-discovered. | Platform | Paths scanned | | ---------------------- | ------------------------------------------------------------------------------------------------------------------------- | | **Claude Code** | `~/.claude/skills`, `./.claude/skills`, `~/.claude/plugins/*/skills/*`, `~/.claude/commands`, `./.claude/commands` | | **OpenClaw / ClawHub** | `~/.openclaw/workspace/skills`, `~/.openclaw/workspace-*/skills` (profiles via `OPENCLAW_PROFILE`), `~/.openclaw/skills` | | **Codex / skills.sh** | `~/.agents/skills`, `./.agents/skills`, `../.agents/skills`, `/etc/codex/skills` | | **Hermes** | `~/.hermes/skills`, `~/.hermes/skills/*` (bundled categories), `./.hermes/skills` | | **Other** (generic) | Any `skills/` directory found within the current project, up to two levels deep | ## Core Commands Every workflow starts from one of four commands. Run them with `npx agentsec` โ no install needed. ```bash # Full audit (scan + policy evaluation). Default command. npx agentsec # Scan only (no policy evaluation) npx agentsec scan # Generate a report from a previously saved audit JSON npx agentsec report audit.json # Manage and inspect policy presets npx agentsec policy list ``` ## Installation `npx agentsec` needs no install. For repeated use, install globally: ```bash # bun (recommended) bun add -g agentsec # npm npm install -g agentsec # pnpm pnpm add -g agentsec # yarn yarn global add agentsec ``` Then drop the `npx` prefix: ```bash agentsec agentsec scan --path ./my-skills ``` ## Flags All flags work with any command. | Flag | Short | Values | Default | Purpose | | ------------ | ----- | ------------------------------- | ---------- | -------------------------------------------------------- | | `--format` | `-f` | `text`, `json`, `sarif`, `html` | `text` | Output format | | `--output` | `-o` | path | stdout | Write report to file | | `--policy` | `-p` | preset name or path | `default` | Apply a policy preset | | `--platform` | | `openclaw`, `claude`, `codex`, `hermes` | auto | Narrow to one agent platform | | `--path` | | path | auto | Custom skill directory to scan | | `--profile` | | `default`, `web3`, `strict` | `default` | Rule profile. `default` auto-detects Web3 skills; `web3` forces the annex on every skill | | `--verbose` | `-v` | | off | Show detailed findings | | `--no-color` | | | off | Disable colored output | | `--help` | `-h` | | | Show help | | `--version` | `-V` | | | Print version | ## Common Recipes ### Show detailed findings and remediation ```bash npx agentsec --verbose ``` ### Scan a specific directory ```bash npx agentsec scan --path ./my-skills ``` ### Target a specific agent platform ```bash npx agentsec --platform claude npx agentsec --platform codex npx agentsec --platform hermes npx agentsec --platform openclaw ``` ### Audit with a strict policy and save JSON ```bash npx agentsec --policy strict --format json --output audit.json ``` ### Generate an HTML report for stakeholders ```bash npx agentsec --format html --output report.html ``` ### Generate a SARIF report for IDE / code-scanning integration ```bash npx agentsec --format sarif --output report.sarif ``` ### List available policy presets ```bash npx agentsec policy list ``` ### Inspect the rules in a preset ```bash npx agentsec policy show strict ``` ### Validate a custom policy config file ```bash npx agentsec policy validate ./my-policy.json ``` ### Replay a previous audit as an HTML report ```bash npx agentsec report audit.json --format html --output report.html ``` ## Policy Presets | Name | Use Case | | -------------------- | -------------------------------------------------------------------- | | `default` | Balanced policy. Blocks critical findings. | | `strict` | Enterprise-grade. Blocks high and critical findings, enforces tests. | | `permissive` | Lenient. Only blocks critical CVEs. Good for development. | | `owasp-agent-top-10` | Built directly from the OWASP Agentic Skills Top 10. | ## Configuration File `agentsec` auto-loads `.agentsecrc`, `.agentsecrc.json`, or `agentsec.config.json` from the current directory (or any parent): ```json { "format": "text", "output": null, "policy": "strict", "verbose": false } ``` CLI flags always override config file values. Omit `"platform"` and `"path"` to keep the default auto-discovery behavior โ agentsec will scan every known platform's default locations. ## OWASP Agentic Skills Top 10 Every audit checks all ten risk categories: | ID | Risk | | ----- | ------------------------------- | | AST01 | Malicious Skills | | AST02 | Supply Chain Compromise | | AST03 | Over-Privileged Skills | | AST04 | Insecure Metadata | | AST05 | Untrusted External Instructions | | AST06 | Weak Isolation | | AST07 | Update Drift | | AST08 | Poor Scanning | | AST09 | No Governance | | AST10 | Cross-Platform Reuse | ## AST-10 Web3 Annex (auto-detected) Web3-touching skills are detected automatically and audited against twelve additional rules โ no flag required. A skill is detected as Web3 when its manifest declares a `web3:` block, when its source imports a Web3 client library (`viem`, `ethers`, `web3`, `wagmi`, `@solana/web3.js`, `@coinbase/onchainkit`, `@privy-io`, `@biconomy`, `@zerodev`), when it references a Web3 RPC method (`eth_*`, `wallet_*`, `personal_sign`, `signTypedData`), or when it ships a `.sol` file. Detected skills are tagged `[Web3]` in the output: ```text โ scoped-trader v1.4.0 [Web3] C (62) โ helpful-summarizer v1.2.0 A (95) ``` `--profile web3` is still available โ it forces the annex onto every skill regardless of detection (useful for cross-team CI consistency): ```bash npx agentsec audit --profile web3 --path ./my-skills ``` | ID | Risk | | ------- | ----------------------------------------------- | | AST-W01 | Unbounded Signing Authority | | AST-W02 | Implicit Permit / Permit2 Signature Capture | | AST-W03 | Delegation Hijack via EIP-7702 | | AST-W04 | Blind / Opaque Signing Surface | | AST-W05 | RPC Endpoint Substitution & Mempool Leakage | | AST-W06 | Unverified Contract Call Targets | | AST-W07 | Cross-Chain / Bridge Action Replay | | AST-W08 | MCP Chain-Tool Drift / Capability Smuggling | | AST-W09 | Session-Key / Permission-Caveat Erosion | | AST-W10 | Slippage / Oracle Manipulation by Agent Loop | | AST-W11 | Key Material in Agent Memory / Logs | | AST-W12 | No On-Chain Action Audit / Kill-Switch | Skills can declare a `web3` block in their manifest (chains, signers, policy caps, session-key scopes, MCP server pinning, audit sink, kill-switch) so the annex can verify scoping without flagging well-bounded skills. See `docs/plans/ast10-web3-annex-rules.md` for full per-rule detection signals. ## Understanding the Output Default output is compact: each skill shows its grade and score, followed by a one-line finding summary and a PASS/WARN/FAIL status. ``` โ Found 6 skills โ fetch-data v1.0.0 D (42) โ deploy-helper v2.3.0 C (68) โ code-review v1.1.0 A (95) 6 skills scanned โข avg score 78 โข 4 certified Findings: 2 critical, 1 high, 2 medium โ WARN 3 high/critical finding(s) detected ``` Use `--verbose` for score breakdowns, rule IDs, file/line locations, and remediation for each finding. ## Exit Codes - `0` โ audit passed the active policy - `1` โ policy violation or fatal error Use the exit code directly to gate CI pipelines โ no special flag required: ```bash npx agentsec --policy strict || exit 1 ``` ## Tips - Start with `npx agentsec` โ no install, no flags. Iterate from there. - Add `--verbose` whenever you need to act on specific findings. - Pipe `--format json` into `jq` or a custom script for programmatic handling. - `strict` is the most common preset for production repositories. - Browse the agent skills ecosystem at [skills.sh](https://skills.sh).skills/agentsec/.gitignore191 B300dd1d7c714upstream โ
# Secrets and credentials .env .env.* *.pem *.key *.crt credentials credentials.json # Reports generated by agentsec itself agentsec-report/ *.sarif # Editor / OS noise .DS_Store Thumbs.dbREADME.mdupstream โ
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/semiotic-ai-agentsec-skills-agentsec.md