---
name: Security Audit
slug: security-audit
category: Quality
description: Security Audit examines a codebase or directory for security issues such as hardcoded secrets, injection, unsafe deserialization, weak cryptography, and authorization gaps, then produces a structured findings report. Use it when asked for a security review or vulnerability audit; it reports findings only and never fixes code.
github: "https://github.com/omnigent-ai/omnigent/tree/main/examples/sentinel/skills/security-audit"
language: Python
stars: 8855
forks: 1336
install: "npx degit https://github.com/omnigent-ai/omnigent/tree/main/examples/sentinel/skills/security-audit ~/.claude/skills/security-audit"
installs_to: ~/.claude/skills/security-audit
source_path: examples/sentinel/skills/security-audit/SKILL.md
collection_size: 24
category_size: 1354
collection_url: "https://dirskills.com/collections/omnigent-ai/omnigent"
added: 2026-08-15T06:50:45.492Z
last_synced: 2026-08-15T06:50:45.492Z
canonical_url: "https://dirskills.com/skills/security-audit"
---

# Security Audit

Security Audit examines a codebase or directory for security issues such as hardcoded secrets, injection, unsafe deserialization, weak cryptography, and authorization gaps, then produces a structured findings report. Use it when asked for a security review or vulnerability audit; it reports findings only and never fixes code.

**Install:**

```bash
npx degit https://github.com/omnigent-ai/omnigent/tree/main/examples/sentinel/skills/security-audit ~/.claude/skills/security-audit
```

## README

# security-audit — review code for security issues, report only

## 1. Collect scope

Identify what to audit (a directory, a diff, a module). Gather it yourself with
sys_os_* / git — this is plumbing, not investigation.

## 2. Dispatch the scanner (purpose: explore / search)

Hand the scanner the scope; it reads source, manifests, history and returns
per-finding evidence. Do NOT sprawl across the repo yourself.

## 3. Synthesize the draft — FINDINGS TEMPLATE (must match orchestrator prompt)

For each finding:

    ### <Severity>: <short title>
    - **Severity**: Critical | High | Medium | Low | Info
    - **Location**: file:line
    - **Recommendation**: <fix guidance — describe it, never apply it>
    - **Confidence**: high | medium | low

## 4. Cross-vendor review (purpose: review)

Route the draft through the reviewer (codex, different vendor) to confirm true
positives and drop false positives. Fold in its verdicts.

## 5. Deliver

Present the final report. You REPORT; you never edit, patch, or fix code.