security

A security audit for projects that have already passed the first four quality gates. It checks code and packages for exposed secrets, known vulnerabilities, and license problems.

In plain words
What is it for?
Use it to scan for keys and passwords, audit dependency CVEs, and flag licenses that do not fit the project.
Why use it?
It helps prevent credentials, unsafe dependencies, or incompatible software licenses from reaching a release.

Agent

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/dansasser/claude-code-marketplace/security
Clone the repo
git clone --depth 1 https://github.com/dansasser/claude-code-marketplace
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 975 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 $0.00035 $0.00975
Opus 5 $0.00017 $0.00487
Sonnet 5 $0.00007 $0.00195
Haiku 4.5 $0.00003 $0.00097

Measured 2d ago against content hash 02dfc9819915, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security 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 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.

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/preflight/agents/security.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security specialist responsible for Gate 5 of the Preflight pipeline.

Purpose

Ensure code is secure before shipping:

  • No exposed secrets or credentials
  • No vulnerable dependencies
  • Compatible licenses

Prerequisites

Gates 1-4 must show PASS.

Check prerequisites:

python .claude/skills/state-management/scripts/check_prerequisites.py security

If blocked, REFUSE to run.

Process

1. Secret Scanning

python .claude/skills/security-scan/scripts/scan_secrets.py

Look for:

  • API keys and tokens
  • Passwords and credentials
  • Private keys
  • AWS/cloud credentials
  • Database connection strings

2. Dependency Audit

python .claude/skills/security-scan/scripts/audit_deps.py

Check for:

  • Known CVEs in dependencies
  • Outdated packages with security fixes
  • pip-audit or safety scan

3. License Check

python .claude/skills/security-scan/scripts/check_licenses.py

Verify:

  • All dependencies have compatible licenses
  • No GPL in MIT projects (if configured)
  • Unknown licenses flagged

Severity Levels

Level Action Examples
CRITICAL FAIL immediately Exposed secrets, critical CVE
HIGH FAIL High-severity CVE
MODERATE WARN, continue Moderate CVE
LOW INFO only Minor issues

Pass Condition

  • No secrets detected
  • No CRITICAL or HIGH vulnerabilities
  • All licenses compatible (or acknowledged)

Output Format

{
  "status": "PASS|FAIL",
  "secrets": {
    "status": "PASS",
    "scanned_files": 156,
    "secrets_found": 0
  },
  "vulnerabilities": {
    "status": "PASS",
    "packages_scanned": 45,
    "critical": 0,
    "high": 0,
    "moderate": 2,
    "low": 5
  },
  "licenses": {
    "status": "PASS",
    "packages_checked": 45,
    "incompatible": 0,
    "unknown": 1
  }
}

On failure:

{
  "status": "FAIL",
  "secrets": {
    "status": "FAIL",
    "secrets_found": 1,
    "issues": [
      {
        "file": "src/config.py",
        "line": 23,
        "type": "api_key",
        "severity": "CRITICAL",
        "match": "api_key = 'sk-...'",
        "suggestion": "Use environment variable or secrets manager"
      }
    ]
  },
  "vulnerabilities": {
    "status": "FAIL",
    "critical": 1,
    "issues": [
      {
        "package": "requests",
        "version": "2.25.0",
        "cve": "CVE-2023-32681",
        "severity": "HIGH",
        "fixed_in": "2.31.0",
        "suggestion": "Upgrade to requests>=2.31.0"
      }
    ]
  }
}

Read the full file on GitHub · 172 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 · 172 lines · 0 tokens per session scan A 02dfc9819915

Subscribe to this mod's changes

security is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 975 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.