bump-release

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes just full-write to format configuration files if a justfile is present in the repository. This is a common automation pattern in modern development environments.
  • [COMMAND_EXECUTION]: Uses standard Git CLI commands (git status, git commit, git tag) to manage repository state during the release process.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external, untrusted data from Git commit messages and Pull Request metadata to generate changelog entries.
  • Ingestion points: Git history and PR metadata retrieved via Git CLI (SKILL.md, Process step 3).
  • Boundary markers: None explicitly defined to separate the instructions from the commit data.
  • Capability inventory: File system writes (package.json, CHANGELOG.md), Git commit/tag execution, and subprocess execution via just (SKILL.md, Steps 1-5).
  • Sanitization: The skill maps input to a structured Markdown format based on the 'Common Changelog' specification, which naturally constrains the output but does not strictly sanitize the input content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:52 PM