changelog-automation

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns or security violations were detected. The skill provides legitimate templates for developer workflows and adheres to industry best practices for version management.
  • [EXTERNAL_DOWNLOADS]: The implementation playbook references the installation of standard tools like semantic-release, standard-version, and commitizen from official package registries (NPM and PyPI). These are well-known services and the downloads are consistent with the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest commit messages and PR descriptions to generate changelogs, which represents a theoretical surface for instruction injection from untrusted commit data.
  • Ingestion points: Git commit history and pull request metadata (referenced in resources/implementation-playbook.md).
  • Boundary markers: Not explicitly implemented in the provided code snippets.
  • Capability inventory: Writing to local files (CHANGELOG.md) and performing Git operations.
  • Sanitization: Not explicitly addressed in the provided templates; the skill relies on the standard behavior of the integrated tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 02:55 AM