ship-branch

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to perform standard development tasks and version control operations.\n
  • Evidence: Instructions specify the execution of npm test, npm run build, npm run lint, git checkout, git merge, git push, and git worktree remove.\n
  • Context: These commands are used as intended for code verification and branch lifecycle management within a local development environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from development branches and commit history to automate the creation of pull request summaries.\n
  • Ingestion points: Implementation code and git commit logs (SKILL.md).\n
  • Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between implementation code and internal instructions during the summarization process.\n
  • Capability inventory: The skill possesses shell execution capabilities (npm, git), file system management (git worktree), and network interaction (git push).\n
  • Sanitization: There is no evidence of content sanitization or validation for the code ingested from the branch before it is included in pull request descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 11:58 PM
Security Audit — agent-trust-hub — ship-branch