/audit
Audit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open switches, weak crypto, permissive access, debug leakage. Parallel sweeps collect candidates, then a refuting verifier traces each one to the security
$ npx -y skills add trailofbits/skills --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/audit
Context preview
What this command does when you run it.
Audit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open switches, weak crypto, permissive access, debug leakage. Parallel sweeps collect candidates, then a refuting verifier traces each one to the security
Command definition
audit.mddescription: "Audit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open switches, weak crypto, permissive access, debug leakage. Parallel sweeps collect candidates, then a refuting verifier traces each one to the security decision it reaches before it is reported." argument-hint: "[path]" allowed-tools: Bash Workflow
Insecure defaults audit
**1. Check the corpus is there.**
ls -1 ${CLAUDE_PLUGIN_ROOT}/referencesMust list `*.md` files. If it errors or lists none, **stop and say so**. Don't search elsewhere, don't guess, don't run the audit anyway.
**2. Run it.** `Workflow` tool:
name: "insecure-defaults:audit-pipeline"
args: { scope: "$1" or ".", pluginRoot: "${CLAUDE_PLUGIN_ROOT}" }Pass the `${CLAUDE_PLUGIN_ROOT}` value as printed above; it's already the real path.
**3. Print the result**, by `status`:
- `findings`, `no-findings-confirmed`: print `report`.
- `no-candidates`: the sweeps ran and matched nothing, which is a real result. There is
no `report`; print `note`, including its point that this is not proof of absence.
- `report-failed`: the audit completed but the write-up died. Print `note`, then present
`findings`, `refuted` and `coverage` yourself.
- anything else: the audit **didn't complete**, so it isn't a clean result. Print `note`
and say the run failed.
A Claude Code plugin marketplace from Trail of Bits providing skills to enhance AI-assisted security analysis, testing, and development workflows. Codex can load this marketplace through its Claude marketplace compatibility.
Other commands on trailofbits-skills.
- /burp-search
Searches Burp Suite project files for security analysis
Open command - /ct-check
Detects timing side-channels in cryptographic code
Open command - /diff-review
Performs security-focused differential review of code changes
Open command - /entry-points
Identifies state-changing entry points in smart contracts
Open command - /scan-apk
Scans Android APKs for Firebase security misconfigurations
Open command - /semgrep-rule
Creates Semgrep rules with test-first methodology
Open command

