beaver-release-skills

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage Git history, tagging, and commits, as well as executing package manager commands like npx, cargo, and twine.
  • [EXTERNAL_DOWNLOADS]: The skill executes @changesets/cli via npx, which may download the package from the official NPM registry.
  • [DATA_EXFILTRATION]: The skill pushes code to remote Git repositories and uploads packages to public registries such as NPM, PyPI, and Crates.io. These operations are the primary intended function of the skill for facilitating software releases.
  • [PROMPT_INJECTION]: The skill analyzes Git diffs and logs to generate release notes, creating an indirect prompt injection surface. This risk is mitigated by the requirement for explicit user confirmation before generating changesets or committing changes.
  • [PROMPT_INJECTION] Evidence Chain:
  • Ingestion points: git log and git diff analyzed in SKILL.md.
  • Boundary markers: Not explicitly defined in the prompts.
  • Capability inventory: File writes, git tagging/committing/pushing, and package publishing commands.
  • Sanitization: Relies on user review and confirmation of AI-generated content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 01:00 PM