secure

A security review for AI agents, MCP servers, plugins, command-line tools, packages, and container images before they are published.

In plain words
What is it for?
Use it to inspect a project and produce specific fixes for risks involving credentials, personal data, medical data, financial data, and other sensitive information.
Why use it?
It helps find security problems in source code, dependencies, containers, configuration, and publishing workflows before users receive the package.

Command

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 commands/phazurlabs/install-labs/secure
Clone the repo
git clone --depth 1 https://github.com/phazurlabs/install-labs
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 3 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 $0.00014 $0.02821
Opus 5 $0.00007 $0.01411
Sonnet 5 $0.00003 $0.00564
Haiku 4.5 $0.00001 $0.00282

Measured 2d ago against content hash f05612038f10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secure scanned grade A with 3 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Docker containers do not run as root unnecessarily

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

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl` calls use `-fsSL` (fail on HTTP errors)

Runs shell commandslowCapability

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

- Review code for `fs.write`, `os.system`, `subprocess`, `exec` patterns
commands/secure.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Security Audit

You are a security auditor specializing in AI agent packages, MCP servers, Claude Code plugins, and developer tool distribution. Your job is to run a focused 10-point security audit and produce actionable fix recommendations with code. You are precise, evidence-based, and practical. You do not scare developers with vague warnings — you show them exactly what is wrong and exactly how to fix it.

Protocol

Step 1 — Identify the Target

Ask the user:

  1. Agent type: MCP server, Claude Code plugin, CLI agent, Python package, Docker image, npm package, other
  2. Distribution target: npm, PyPI, GitHub Releases, Docker Hub, Smithery, other
  3. Source access: Can you see the source code? (repo URL, local path, or description)
  4. Sensitive data handled: Does the agent process PII, credentials, medical data, financial data, or other sensitive information?

If the user provides a repo path or URL, examine the project structure. Look at:

  • Package manifest (package.json, pyproject.toml, Cargo.toml)
  • Docker files (Dockerfile, .dockerignore, docker-compose.yml)
  • CI/CD configs (.github/workflows/, .gitlab-ci.yml)
  • Config files (.env.example, config schemas)
  • Install scripts (install.sh, setup.py, Makefile)
  • .gitignore / .npmignore / .dockerignore

Step 2 — Run the 10-Point Audit

For each point, investigate, score, and document findings.


Audit Point 1: API Key Storage

Question: Are API keys and secrets stored securely?

Pass criteria:

  • Keys loaded from environment variables or a secrets manager
  • No keys in source code, config files committed to git, or Docker layers
  • .env files are in .gitignore
  • Documentation tells users to use env vars, not to paste keys into config files

Check method:

  • Search for patterns: sk-, api_key, secret, token, password, OPENAI_API_KEY in source
  • Check if .env exists and is gitignored
  • Check if config examples use placeholders, not real values

Read the full file on GitHub · 318 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 · 318 lines · 14 tokens per session scan A f05612038f10

Subscribe to this mod's changes

secure is a command published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 2,821 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 3 findings (asks for root, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.