audit-security

A code-level security review that looks for vulnerabilities in your own source code, such as exposed secrets, injection risks, and missing access checks. It produces a prioritized remediation plan with severity ratings.

In plain words
What is it for?
Use it to scan a whole repository or a selected path for hardcoded keys and passwords, SQL or command injection, unsafe deserialization, missing access controls, and other common web-application risks.
Why use it?
It helps identify weaknesses attackers could exploit before they become security incidents, including unsafe defaults and missing authentication or authorization.

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/tomzx/agents/audit-security
Any agent
npx skills add tomzx/agents --skill audit-security
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00035 $0.02417
Opus 5 $0.00017 $0.01208
Sonnet 5 $0.00007 $0.00483
Haiku 4.5 $0.00003 $0.00242

Measured 3d ago against content hash 84b47b74139c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-security scanned grade A with 1 finding 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 3d ago.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

rg -n "(os\.system|subprocess\.(call|run|Popen)|exec\(|eval\(|child_process)" \
skills/audit-security/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TODAY=!date +%Y-%m-%d

Security Audit

Scans your own code for vulnerabilities — distinct from /audit-dependencies which covers external packages. Covers hardcoded secrets, injection patterns, missing authentication and authorization checks, insecure defaults, and other OWASP-class issues. Produces a prioritized remediation plan with severity ratings.

Prerequisites

  • Working directory is the root of the repository
  • Optional: $1 — path to limit the scan (defaults to .)
  • Language-specific tools (degrades to rg heuristics if unavailable):
    • Any language: semgrep (pip install semgrep or brew install semgrep)
    • Secrets: trufflehog (pip install trufflehog) or gitleaks (brew install gitleaks)
    • Python: bandit (uv tool install bandit)
    • JavaScript/TypeScript: eslint with eslint-plugin-security
    • Go: gosec (go install github.com/securego/gosec/v2/cmd/gosec@latest)

Vulnerability Categories

Category Severity Examples
Hardcoded secrets 🔴 Critical API keys, passwords, tokens in source
Injection 🔴 Critical SQL, command, LDAP, XPath injection
Insecure deserialization 🔴 Critical pickle.loads, eval, exec on user input
Broken authentication 🔴 High Missing auth checks, weak session handling
Sensitive data exposure 🔴 High PII/secrets logged, transmitted unencrypted
Insecure direct object reference 🟡 High Missing ownership checks on resource access
Security misconfiguration 🟡 Medium Debug mode on, permissive CORS, weak TLS
Missing authorization 🟡 Medium Authenticated but not authorized
Cryptography issues 🟡 Medium Weak algorithms (MD5, SHA1), hardcoded IVs
Dependency confusion 🟢 Low Internal package names resolvable publicly

Steps

1. Detect Language and Available Tools

find ${1:-.} -type f | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -10
command -v semgrep && semgrep --version
command -v bandit && bandit --version
command -v gosec && gosec --version
command -v gitleaks && gitleaks version
command -v trufflehog && trufflehog --version

Read the full file on GitHub · 244 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. 3d ago First seen · 244 lines · 35 tokens per session scan A 84b47b74139c

Subscribe to this mod's changes

audit-security is a skill published in the GitHub repository tomzx/agents (5 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 2,417 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens