skills/cedanl/.github/ship/Gen Agent Trust Hub

ship

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard development tools including git, gh (GitHub CLI), pytest, and ruff for code verification and repository management.
  • [DATA_EXFILTRATION]: Instructions include unsetting the GITHUB_TOKEN environment variable locally to resolve authentication conflicts with the gh CLI tool. This is a standard troubleshooting step for command-line authentication and does not involve exfiltrating secrets.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes code diffs and file content during the review and commit workflow. This creates a surface for indirect instructions within code changes, but the skill mitigates this by requiring explicit review and verification steps before committing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:16 AM