Borrowing it
Nothing to install: this file belongs to Nano-Nimbus/locus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Nano-Nimbus/locus/main/.github/prompts/claude-security-audit.mdgit clone --depth 1 https://github.com/Nano-Nimbus/locusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/nano-nimbus/locus/claude-security-audit)<a href="https://agentmods.dev/commands/nano-nimbus/locus/claude-security-audit"><img src="https://agentmods.dev/badge/commands/nano-nimbus/locus/claude-security-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/nano-nimbus/locus/claude-security-audit"><img src="https://agentmods.dev/badge/commands/nano-nimbus/locus/claude-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00488 |
| Opus 5.5 | $0.00000 | $0.00195 |
| Sonnet 5.5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
claude-security-audit 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 1mo 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.
What it actually says
Claude GitHub Action Prompt: Security Audit + Reporting
You are running in GitHub Actions on this repository. Perform a security-focused audit and produce actionable artifacts.
Objectives
- Run security-relevant tests and scans.
- Identify vulnerabilities, attack vectors, and exploitability.
- Produce a full markdown report and a short PR-ready summary comment.
Required Execution Plan
- Install dependencies:
uv sync --extra dev
- Run baseline tests:
uv run pytest tests/unit/ -v --tb=short
- Run security scanners and save artifacts:
mkdir -p docs/audits/artifactsuv run --with bandit bandit -r locus -f json -o docs/audits/artifacts/claude-bandit.json || trueuv run --with pip-audit pip-audit > docs/audits/artifacts/claude-pip-audit.txt 2>&1 || true
- Perform targeted manual review of:
locus/mcp/*.pylocus/agent/*.py.github/workflows/*.ymlpyproject.toml
Report Requirements
Write a full report to:
docs/audits/claude-security-pr-review-report.md
Report sections must include:
- Executive summary
- Scope and methods
- Findings ordered by severity
- For each finding:
- Rule ID
- Severity (
Critical/High/Medium/Low) - Location (file + line)
- Evidence
- Impact
- Exploit scenario
- Recommended fix
- Mitigation if fix cannot land now
- Scanner outputs summary
- Merge recommendation (
approveorrequest changes)
PR Comment Output
Also write a concise comment draft to:
docs/audits/claude-security-pr-comment.md
The comment must include:
- Top blocking findings (if any)
- Commands executed
- Artifact paths
- Clear merge recommendation
Quality Bar
- Do not claim vulnerabilities without concrete evidence.
- Use exact file paths and line numbers.
- If no significant issues are found, explicitly say so and list residual risks.
- Prefer practical fixes with minimal regression risk.
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.
- 1mo ago First seen · 69 lines · 0 tokens per session scan A 8dd6d770d37b
claude-security-audit is a command published in the GitHub repository Nano-Nimbus/locus (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 tokens. 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 2026-09-08.
Other commands, from other repositories
dart-fix-ci
Command "dart-fix-ci" from dartsim/dart, covering required reading, workflow and output.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
check-release-health
Summarize the CI health of an OpenShift release using live data from the openshift-ci-mcp server.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
security-check
Fast security baseline audit of a product — tracked secrets, unpinned/vulnerable GitHub Actions, workflow permission scope, untrusted-input triggers, MCP-config surface, and an RLS reminder. Add --live to also check the RUNNING system for drift (live RLS status, storage-bucket visibility, Security Advisors, preview…