cli-command

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for running standard development and validation commands, including pnpm typecheck, pnpm test, and pnpm run validate:boundaries within the local environment.
  • [DATA_EXFILTRATION]: The skill documents access to ~/.composio/user-config.json and project-local .composio/ directories for managing authentication and state. It incorporates a security principle to never accept secrets via command-line flags to prevent sensitive data exposure in shell history.
  • [REMOTE_CODE_EXECUTION]: Guidelines mandate the use of the @effect/platform abstraction layer for filesystem and subprocess operations, specifically banning raw Node.js modules like fs and child_process in the source directory to enforce structured and safer resource handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 09:21 AM
Security Audit — agent-trust-hub — cli-command