bump-version

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and the uv package manager to update configuration files and manage repository state.
  • [PROMPT_INJECTION]: Indirect prompt injection surface via git history ingestion.
  • Ingestion points: git log output (SKILL.md)
  • Boundary markers: None
  • Capability inventory: git tag, git push, uv lock
  • Sanitization: None The risk is assessed as safe because the ingested data is used strictly for version classification in a standard development workflow.
  • [DATA_EXFILTRATION]: The skill leverages OIDC for PyPI releases, which is a security best practice that avoids the use of hardcoded credentials or manual secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 09:20 AM
Security Audit — agent-trust-hub — bump-version