release

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard CLI tools including npm run release, git (fetch, checkout, cherry-pick, push), and composer changelog:write to automate versioning and release tasks. These actions are standard for software development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a process that ingests data from external sources, specifically Pull Request descriptions, to automatically generate changelogs. While this presents an injection surface, the risk is mitigated by a required manual review step (review and merge the PR) and automated validation via GitHub Actions as noted in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 03:01 AM
Security Audit — agent-trust-hub — release