audit-security

A multi-agent security audit workflow that checks a codebase for problems in authentication, input validation, data exposure, and infrastructure.

In plain words
What is it for?
Use it to audit or harden a codebase, review authentication and validation, scan for vulnerabilities, and produce an audit report. It normally requires an earlier implementation-completeness report.
Why use it?
It provides a structured review against the project’s security requirements and identifies weaknesses that could expose users, data, or systems.

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/voxtechnologies/transmute-framework/audit-security
Any agent
npx skills add VoxTechnologies/transmute-framework --skill audit-security
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,464 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00083 $0.03464
Opus 5 $0.00042 $0.01732
Sonnet 5 $0.00017 $0.00693
Haiku 4.5 $0.00008 $0.00346

Measured 2d ago against content hash 87148825f6db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

audit-security scanned grade B 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 2d 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

7. ALWAYS verify SSRF blocklist: check all outbound `fetch()` or HTTP client calls triggered by user input. Reject private IP ranges (10.x, 172.16-31.x, 192.168.x), localhost (127.0.0.1, ::1), link-local (169.254.x, fe80

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

skills/audit-security/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit — Stage 6A

Read the detailed guide at ${CLAUDE_SKILL_ROOT}/references/audit-security-detailed-guide.md for the complete audit procedures, teammate spawn prompts, vulnerability fix patterns, and report templates.

Lead a multi-agent security audit of the complete codebase against BRD security requirements and PRD security specifications. Identify vulnerabilities and fix them.

Stage Sequence (recommended ordering): Stage 5B → (6A (this stage) ‖ 6B ‖ 6C) → 6E → 6F → 6G → 6D → 6H → 6V → 6R → 6P/6P-R → 7 (Deploy). Note: 6A, 6B, and 6C run in parallel (each in a separate session). If running in parallel, commit 6A changes as soon as 6A completes to avoid config file conflicts — see CLAUDE.md § "Stage 6 ordering".

Prerequisite Checks

Before any audit work, verify:

  1. Check that ./plancasting/_audits/implementation-completeness/report.md exists and shows PASS or CONDITIONAL PASS. If missing, STOP: 'Stage 5B report not found — run Stage 5B before starting Stage 6 audits. Proceeding without 5B wastes effort on incomplete code.' (Override: if the operator explicitly confirms 5B was intentionally skipped, proceed with a WARN in the report noting unverified implementation completeness.)
  2. If 5B shows FAIL, STOP — the codebase has unresolved implementation gaps that must be fixed before security auditing. If CONDITIONAL PASS, note the documented Category C issues — skip security auditing for those incomplete features.
  3. Read ./CLAUDE.md and ./plancasting/tech-stack.md for project conventions.
  4. Read the relevant PRD sections for implementation context.

Inputs

Read and reference these files throughout the audit:

  • Codebase: Backend directory and ./src/ (adapt paths per tech stack)
  • Tech Stack: ./plancasting/tech-stack.md
  • Security Requirements: ./plancasting/brd/13-security-requirements.md
  • Compliance Requirements: ./plancasting/brd/12-regulatory-and-compliance-requirements.md
  • PRD Security Architecture: ./plancasting/prd/10-system-architecture.md (auth/authz section)
  • PRD API Specs: ./plancasting/prd/12-api-specifications.md (auth scheme, rate limiting)
  • Project Rules: ./CLAUDE.md

Read the full file on GitHub · 187 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 187 lines · 83 tokens per session scan B 87148825f6db

Subscribe to this mod's changes

audit-security is a skill published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 3,464 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). 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

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…

wonderwhy-er/DesktopCommanderMCP · 112 tokens

code-review

Use when code has been written and needs validation before committing, or when the user asks for a code review or security check.

darrenhinde/OpenAgentsControl · 28 tokens

test-generation

Use when the user asks for tests, mentions TDD, or when new code has been written and needs test coverage.

darrenhinde/OpenAgentsControl · 27 tokens

scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…

xintaofei/codeg · 68 tokens

statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…

xintaofei/codeg · 190 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens