skills/tenzir/ship/tenzir-ship/Gen Agent Trust Hub

tenzir-ship

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes uvx to download and execute the tenzir-ship utility from the Python Package Index (PyPI). This is a well-known service and the package is a verified resource belonging to the skill's author ('tenzir').
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests git diffs and file lists to automatically generate changelog titles and descriptions.
  • Ingestion points: Output of the scripts/detect-change-scope.sh script and git diff commands in the repository.
  • Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between diff content and agent instructions.
  • Capability inventory: The agent has the ability to write files, commit to git, create tags, and trigger GitHub Actions workflows using tenzir-ship and gh CLI tools.
  • Sanitization: There is no explicit sanitization or validation of the code diffs before they are processed by the agent to create user-facing text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 01:50 AM
Security Audit — agent-trust-hub — tenzir-ship