jackin-merge-pr

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes gh, git, cargo, and bun to perform repository management tasks. Specifically, it uses cargo run -p jackin-pr-trailers and cargo xtask roadmap for project-specific automation. These tools are standard within the vendor's development ecosystem.
  • [PROMPT_INJECTION]: The skill processes untrusted content from pull request views, diffs, and documentation files.
  • Ingestion points: Pull request metadata (titles, bodies) and file diffs are read via gh pr view and gh pr diff from SKILL.md.
  • Boundary markers: Employs a 'Blast-radius classification' strategy that requires explicit manual confirmation for pull requests affecting security surfaces, workflows, or schemas.
  • Capability inventory: The agent is authorized to perform high-privilege actions including gh pr merge, gh pr edit, and git push upon successful verification of gates.
  • Sanitization: Instructions mandate a 'fail-closed' approach where the agent must stop and confirm if CI checks are pending/failing or if authorization is not clearly established.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 05:10 AM
Security Audit — agent-trust-hub — jackin-merge-pr