absolute-audit — Claude Code skill: security audit
absolute-audit — a security-audit skill for Claude Code checks dependencies for CVEs and scans code for risky patterns. It activates on requests to audit security, find secrets, or harden a repository.
MIT 592 installs ★ 224 updated 2026-10-26
npx skills add dhruvjainin/absolute --skill absolute-audit -a claude-codeWhat absolute-audit does
absolute-audit scans the committed repository for vulnerable dependencies and risky code, including exposed credentials, unsafe input handling, and missing access checks. It ranks findings by severity, exploitability, and whether application paths can reach them, then proposes fixes and scans again.
Secrets are reported by file and line, never printed. The skill verifies fixes without suppressing alerts; exposed live credentials are flagged for rotation. The built-in /security-review examines pending changes on a branch, while absolute-audit covers the committed repository and its dependencies.
Install it in Claude Code with npx skills add dhruvjainin/absolute --skill absolute-audit -a claude-code. The skill file is at ~/.claude/skills/absolute-audit/SKILL.md.
What it helps with
- find CVEs in project dependencies
- spot exposed secrets and risky code patterns
- prioritize vulnerabilities by severity and reachability
- apply fixes and rerun the security scan
Example prompts for the agent
- Audit the security of the whole repository.
- Check our dependencies for CVEs and look for exposed secrets.
- Harden the routes and fix the vulnerabilities you find.
How to install absolute-audit
1Skills CLI (Vercel)
npx skills add dhruvjainin/absolute --skill absolute-audit -a claude-code2Manually: put the files in place
~/.claude/skills/absolute-audit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/absolute-audit/
1Skills CLI (Vercel)
npx skills add dhruvjainin/absolute --skill absolute-audit -a codex2Manually: put the files in place
.agents/skills/absolute-audit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add dhruvjainin/absolute --skill absolute-audit -a cursor2Manually: put the files in place
.cursor/skills/absolute-audit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install dhruvjainin/absolute skills/absolute-audit2Manually: put the files in place
.github/skills/absolute-audit/SKILL.md1Skills CLI (Vercel)
npx skills add dhruvjainin/absolute --skill absolute-audit -a gemini-cli2Platform CLI
gemini skills install https://github.com/dhruvjainin/absolute --path skills/absolute-auditManually: put the files in place
.devin/skills/absolute-audit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add dhruvjainin/absolute --skill absolute-audit -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about absolute-audit
How do I install absolute-audit in Claude Code?
Run npx skills add dhruvjainin/absolute --skill absolute-audit -a claude-code. The skill file is stored at ~/.claude/skills/absolute-audit/SKILL.md.
What does absolute-audit do?
It checks dependencies for CVEs and scans code for risky patterns, then ranks findings and helps remediate them. It reruns the scan after fixes and does not resolve alerts by suppressing them.
How is absolute-audit different from /security-review?
/security-review reviews pending changes on the current branch. absolute-audit scans the committed repository, including its dependencies.
Source text
SKILL.md · MIT
--- name: absolute-audit version: 0.5.0 description: > Vulnerability and security scan (defensive, your own repo): dependency CVEs plus risky code patterns (secrets, injection, weak authz), severity x reachability triaged and remediated without suppressing. Complements the built-in /security-review. Triggers on "absolute audit", "security audit", "are we vulnerable", "scan for CVEs", "check for secrets/injection", "harden this". category: workflow tags: - workflow - security - audit - vulnerabilities - cve platforms: - claude-code - gemini-cli - openai-codex - mcp user-invocable: true argument-hint: "[target]" license: MIT maintainers: - github: maddhruv --- > Start your first response with the 🔒 emoji. ## Absolute Audit Find and triage security problems across the repo — vulnerable dependencies (CVEs) and risky code patterns — then fix the ones worth fixing, safely. Output is a severity-ranked findings table with a remediation per item, not a raw scanner dump. Runs the shared engine in **`references/health-engine.md`** — read it for the DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file covers only what's specific to security auditing. > **Authorized defensive use.** This command audits the user's *own* repository to find > and fix weaknesses. It is for hardening, not for attacking systems or evading detection. --- ## When to use - "Run a security audit", "are we vulnerable?", "check our deps for CVEs". - After a CVE disclosure affecting something you use. - Periodic hygiene on `main`. Distinct from the built-in **`/security-review`** (reviews the *pending diff* on your branch) — `audit` scans the **whole committed repo**, deps included. They complement. --- ## What it scans **1. Dependency vulnerabilities (CVEs)** — primary: | Ecosystem | Scanner | |---|---| | npm / pnpm / yarn | `npm audit --json` / `pnpm audit --json` / `yarn npm audit --json` | | Python | `pip-audit` (preferred) or `safety check` | | Go | `govulncheck ./...` | | Cross-language | `osv-scanner` against the lockfile if available | **2. Code-level patterns** — read-only grep/static pass for high-signal issues only: hardcoded secrets/keys/tokens, `eval`/dynamic exec on input, SQL built by string concatenation, missing authz checks on sensitive routes, disabled TLS verification, unsafe deserialization, overly-broad CORS. Prefer the project's existing SAST/linter security rules (`eslint-plugin-security`, `bandit`, `gosec`) if configured. Report suspected leaked secrets but **never print the secret value** — reference `path:line` and the kind. --- ## Risk ranking (TRIAGE) Rank by **severity × exploitability × reachability**, not raw CVSS: | Severity | Default | |---|---| | Critical / High, reachable, fix available | fix now (wave 1) | | Moderate, reachable | fix this pass | | Low / not reachable from app code | report, usually defer | | Transitive-only, no direct upgrade path | flag, note the blocking parent | Mark each: is it reachable from the app's actual code paths? A CVE in an unused transitive branch is lower priority than a Moderate one on a hot path. State the fixed version or the mitigation for each. --- ## Fix & verify - **Dep CVEs** → resolve via the smallest version move that clears it (delegate the actual bump mechanics to the `upgrade` flow's per-ecosystem steps). Prefer patched minors; escalate to a major only when that's the only fix, and gate it. - **Code issues** → apply the concrete fix (parameterize the query, move the secret to env + flag the leaked one for rotation, add the authz check). Each fix is its own small wave. - After each wave, re-run the scanner: the finding must actually disappear, and tests/build stay green. Never resolve by suppressing/allowlisting the alert. - Leaked live secrets: flag for **rotation** — removing from code doesn't undo exposure. --- ## Gotchas 1. **Audit fatigue → blanket ignore.** Triage by reachability instead of muting the scanner. 2. **Fixing a CVE by suppressing it.** An allowlisted advisory is still a vulnerability. 3. **Printing the secret.** Reference location + type only; never echo the value. 4. **Deleting a secret from code ≠ safe.** It's in git history and was exposed — rotate it. 5. **Stopping at deps.** Many real issues are in code, not the dependency tree — run both passes. --- ## Companion commands - **`/absolute upgrade`** — does the actual version moves for vulnerable deps. - **`/security-review`** (built-in) — pair with this to also cover your pending diff. - **`/absolute work`** — if remediation is a real refactor (e.g. replacing an auth flow), hand off.
© dhruvjainin · MIT · dhruvjainin/absolute