signed-audit-trails-recipe

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install and run tools from the NPM registry and PyPI, specifically protect-mcp, @veritasacta/verify, and protect-mcp-adk. These are presented as the core components of the auditing solution.
  • [REMOTE_CODE_EXECUTION]: Configuration examples utilize npx, which involves downloading and executing remote code from the NPM registry at runtime. Specifically, the hooks are configured to run npx protect-mcp@latest.
  • [COMMAND_EXECUTION]: The guide recommends setting up PreToolUse and PostToolUse hooks that execute shell commands. These commands are triggered by agent tool calls to perform policy evaluation and cryptographic signing.
  • [DATA_EXPOSURE]: The skill involves the generation and handling of an Ed25519 private key (protect-mcp.key). The documentation correctly advises users to add this file to .gitignore and avoid committing it to version control.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 06:31 PM