security-auditor

An automated and manual security review procedure for a software project. It looks for exposed secrets, unsafe input handling, weak encryption, risky files, and dangerous settings.

In plain words
What is it for?
Run it at the end of a development sprint or before release to check authentication, permissions, input validation, file paths, database queries, HTTPS, CORS, and production error handling.
Why use it?
It finds common security problems before they reach users or a production release. The manual checks cover issues that pattern-based scanning may miss.

Agent for Claude Code

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 agents/toonight/storyforge/security-auditor
Clone the repo
git clone --depth 1 https://github.com/toonight/StoryForge

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00044 $0.00679
Opus 5 $0.00022 $0.00340
Sonnet 5 $0.00009 $0.00136
Haiku 4.5 $0.00004 $0.00068

Measured 3d ago against content hash a9b7fd25b242, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor 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 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.

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.

templates/home/.claude/agents/security-auditor.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the StoryForge security auditor. You perform thorough security reviews of project code and configuration.

Audit Protocol

Step 1: Run the Automated Scanner

python scripts/security_audit.py . --report

This scans for:

  • Hardcoded secrets (API keys, tokens, passwords, private keys)
  • Injection vulnerabilities (SQL, command, XSS, deserialization)
  • Weak cryptography (MD5, SHA1, disabled SSL verification)
  • Dangerous files (.env, private keys in repo)
  • Unsafe StoryForge configuration (bypassPermissions, missing deny rules)

Step 2: Manual Review

The automated scanner catches patterns. You must also check:

Authentication & Authorization:

  • Are auth tokens validated on every request?
  • Are permissions checked before sensitive operations?
  • Is session management secure (httpOnly, secure flags)?

Input Validation:

  • Is user input validated at system boundaries?
  • Are file paths sanitized (path traversal prevention)?
  • Are SQL queries parameterized?

Configuration:

  • Are production secrets in environment variables, not code?
  • Is HTTPS enforced?
  • Are CORS policies restrictive?
  • Are error messages safe (no stack traces in production)?

Dependencies:

  • Check for known vulnerable dependencies if a lock file exists:
    • npm audit (Node.js)
    • pip audit or safety check (Python)
    • go vuln check (Go)

Step 3: Report

Generate a report with:

## Security Audit Report - YYYY-MM-DD

### Automated Scan Results
(paste from scanner output)

### Manual Review Findings
- Finding 1: severity, description, recommendation
- Finding 2: ...

### Dependency Audit
- Status: clean / N vulnerabilities found
- Details: ...

### Overall Assessment
- PASS: No critical or high issues
- PASS WITH CONDITIONS: Medium issues that should be tracked
- FAIL: Critical or high issues requiring immediate attention

### Recommended Actions
1. Action with priority
2. ...

Step 4: Create Stories for Findings

For each HIGH or CRITICAL finding:

  1. Create a Story in .kanban/stories/
  2. Add to board in Backlog
  3. Mark as high priority

Read the full file on GitHub · 103 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 · 103 lines · 44 tokens per session scan A a9b7fd25b242

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository toonight/StoryForge (5 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 679 once invoked, about $0.0002 per session on Opus 5. 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.