smithery.ai

aaw-security

Enforces security rules for AAW sessions. Activated automatically when handling sensitive operations, external connections, package installations, or file access to protected paths.

First seen Apr 15, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsmcp__aawctl__exec, mcp__aawctl__read_policy, Read, Glob, Grep

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,291 B
  • docs SUMMARY.md 201 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

AAW Security Rules

This skill enforces security policies for all AAW operations.

Absolute Prohibitions

1. Secrets and Credentials

NEVER do these:

  • Read .env, .env.*, or any environment files
  • Read files in secrets/ directories
  • Read files named credentials, .pem, *.key
  • Log, output, or display secret values
  • Commit secrets to version control
  • Store secrets in code comments

If you need secrets:

  • Ask the user to provide them securely
  • Use environment variables at runtime
  • Reference secret management systems

2. Dangerous Commands

NEVER execute:

  • rm -rf / or similar destructive commands
  • sudo anything
  • chmod 777 or overly permissive permissions
  • Commands that modify system files
  • Commands that disable security features

3. External Connections

NEVER do:

  • curl or wget to unknown domains
  • Direct API calls to external services (use aawctl)
  • Download and execute scripts from the internet
  • Connect to databases without going through aawctl

Controlled Operations

Package Installation

When installing packages:

  1. Check approval status

- Is the package in the approved list? - Is it from a trusted registry?

  1. If not approved:

- STOP immediately - Report the package name and version - Wait for explicit approval

  1. Log the installation

- Use mcpaawctlexec for npm/yarn/pnpm - Provide purpose: "Installing package X for Y feature"

File Access

When accessing files:

  1. Check against deny patterns:

- .env - DENIED - secrets/ - DENIED - /credentials - DENIED - **/*.pem, **/*.key - DENIED

  1. If denied:

- Do not attempt to read - Report the access attempt - Suggest alternatives

External API Calls

When making external calls:

  1. Use approved endpoints only
  2. All calls must be logged through aawctl
  3. No direct curl/wget

Incident Response

If you detect a potential security violation:

  1. STOP - Do not proceed with the action
  2. LOG - Record the incident details
  3. REPORT - Inform the user immediately
  4. WAIT - Do not continue without explicit approval

Security Logging

All security-relevant events are logged:

  • Policy check results
  • Denied access attempts
  • Package installations
  • External connections

Logs are included in the evidence bundle.

Policy Enforcement Modes

Audit-Only Mode (Default for PoC)

  • Violations are LOGGED but not BLOCKED
  • Tagged as policycheck: WOULDBLOCK
  • Use for initial rollout and tuning

Enforce Mode (Production)

  • Violations are BLOCKED
  • Operation fails with error message
  • Requires explicit override (if allowed)

Quick Reference

Action Rule
Read .env DENIED
Run sudo DENIED
curl external DENIED
npm install (approved) ALLOWED
npm install (unknown) ASK
Edit source files ALLOWED
Edit node_modules DENIED