dev-team

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands for running tests, linting, and performing git operations. These actions are restricted to a defined workspace path provided by the operator.
  • [PROMPT_INJECTION]: The skill is designed to handle an 'indirect prompt injection' surface (Category 8) by processing a 'Verbatim spec' from potentially untrusted sources. It mitigates this risk by employing a multi-agent loop where a separate QA agent is explicitly instructed to 'Trust nothing' and perform independent verification, including a 'mental revert' check to ensure tests are valid and not just 'theater'.
  • [SAFE]: The skill enforces several security-conscious 'hard rules', such as forbidding git add -A (to prevent accidental inclusion of untrusted or sensitive files) and prohibiting the use of --no-verify (to ensure git hooks are always executed).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:39 AM
Security Audit — agent-trust-hub — dev-team