What is codebase-security-audit?

A code-security auditing add-on that looks for exploitable weaknesses in source code or an entire codebase.

Use it to check for injection, broken authorisation, exposed secrets, memory-safety problems, unsafe deserialisation, SSRF, and risky dependencies. It is not intended for deep cryptography or binary verification.

It helps filter out findings that cannot realistically be reached or cause meaningful harm, so the report focuses on actionable security risks.

codebase-security-audit — Plugin by Quant-Off

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add Quant-Off/skills

agentmods

npx agentmods add plugins/quant-off/skills/codebase-security-audit

Clone the repo

git clone --depth 1 https://github.com/Quant-Off/skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

codebase-security-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/codebase-security-audit/.claude-plugin/plugin.json · 21 lines

What it actually says

{
  "name": "codebase-security-audit",
  "description": "Audits a codebase or file for exploitable vulnerabilities across injection, authorization, secrets, memory safety, deserialization, SSRF, and dependency risk, gating every candidate through six reachability and impact reviews before reporting. Not for deep crypto review or binary verification.",
  "version": "0.2.0",
  "author": {
    "name": "Quant-Off",
    "url": "https://github.com/Quant-Off"
  },
  "homepage": "https://github.com/Quant-Off/skills/tree/main/plugins/codebase-security-audit",
  "repository": "https://github.com/Quant-Off/skills",
  "license": "MIT",
  "keywords": [
    "security-audit",
    "zero-trust",
    "sast",
    "vulnerability",
    "false-positive-filtering",
    "code-review"
  ]
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 21 lines scan A 01d03a1328cb

Subscribe to this mod's changes

codebase-security-audit is a plugin published in the GitHub repository Quant-Off/skills (1 stars, last pushed 22d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Memory and context Security agent-skills ai-agents appsec claude-code claude-code-plugin claude-skills

codebase-security-audit

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

endorlabs

fortify

web-app-security

web-app-security-skill

websec-plugins

claude-cybersecurity