security-audit

A security review workflow for finding vulnerabilities in code, dependencies, infrastructure settings, APIs, secrets, and AI-agent systems.

In plain words
What is it for?
It supports OWASP-based assessments, external security scanners, threat modeling, semantic code review, and checks for agent or MCP risks.
Why use it?
It combines repeatable pattern scanning with a deeper review of authorization, data flows, and attack scenarios that simple scanners can miss.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/matrixfounder/agentic-development/security-audit
Any agent
npx skills add MatrixFounder/Agentic-development --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,258 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.03258
Opus 5 $0.00022 $0.01629
Sonnet 5 $0.00009 $0.00652
Haiku 4.5 $0.00004 $0.00326

Measured 2d ago against content hash 08645e5e1a56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

security-audit scanned grade B with 2 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 2d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/audit/__init__.py, scripts/audit/config.py, scripts/audit/external.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

1. **Prompt Injection (LLM01)**: Can user input override system prompts?

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads MCP configurationlowAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- **MCP / Agentic (OWASP ASI Top 10 2026)** — MCP config provenance (`mcp.json`, `.mcp.json`, `claude_desktop_config.json`, incl. `.vscode/`), auto-approve keys, permission-bypass flags, unpinned `npx -y`/`uvx` servers,

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.agent/skills/security-audit/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit v3.7

0. Methodology — Two Layers (audit-067 C-10)

This skill runs two complementary layers; neither substitutes for the other:

  1. Deterministic floor (§2) — regex patterns + external scanners. Reproducible, cheap, CI-gateable (--fail-on), zero judgment. It is a floor, not the audit: a clean scan is not clearance, because regex is categorically blind to semantic classes — business-logic authz, cross-file taint flows, semantic MCP tool-description poisoning (§3 Agentic limitation note).
  2. LLM semantic pass (§3–§4) — long-context taint/logic review against the checklists plus threat modeling: the layer that catches what regex cannot. Frontier evidence that LLM-driven semantic review finds real vulnerabilities beyond pattern matching: DARPA AIxCC finals (2025), Google Big Sleep, Codex Security / Claude Code Security review agents (full citations: audit-067 §Bibliography).

Licensing footnote (semgrep): the open-source offering is Semgrep CE since the Dec 2024 licensing change; Opengrep (community fork, Jan 2025) is a drop-in alternative where CE constraints matter. The external-tool roster treats either as the same scanner slot.

1. Red Flags (Anti-Rationalization)

STOP and READ THIS if you are thinking:

  • "I'll skip the script because I just checked the code manually" -> WRONG. Humans miss regex patterns. EXECUTE the script.
  • "I have no way to run it, so I'll write down what it would have said" -> WRONG, and the worst of them. Inventing scanner output manufactures a passed gate nobody can see through. There is exactly ONE legitimate way not to execute — §2's NOT RUN branch — and it is legitimate precisely because it is visible.
  • "This is an internal tool, so AuthZ doesn't matter" -> WRONG. Zero Trust applies everywhere.
  • "Dependencies are probably fine" -> WRONG. Supply chain attacks are the #1 vector.
  • "I don't have time for a full audit" -> WRONG. Breach cleanup takes 100x longer.
  • "The LLM output is safe to use directly" -> WRONG. LLM output is untrusted input. Sanitize it.

Read the full file on GitHub · 161 lines

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.

  1. 2d ago First seen · 161 lines · 43 tokens per session scan B 08645e5e1a56

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 43 tokens to every session and 3,258 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (instruction-override phrasing, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens

extension-creator

Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…

QwenLM/qwen-code · 96 tokens

notion

Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.

elizaOS/eliza · 69 tokens

pr-feedback

Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.

strands-agents/harness-sdk · 44 tokens

argent-native-profiler

Native profiling for CPU hotspots, UI hangs, memory issues. iOS via xctrace; Android via Perfetto. Use when diagnosing native-level performance issues.

software-mansion/argent · 37 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens