Skills
Navigate
skills/hburaktasyurek/agent-skills-and-commands/pr-branch/Gen Agent Trust Hub

pr-branch

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content which could contain malicious instructions.
  • Ingestion points: Data is read from git log, git diff, and gh pr view as defined in SKILL.md.
  • Boundary markers: Explicit instructions in SKILL.md warn to treat repository files and Git output as untrusted content.
  • Capability inventory: The skill performs file writing to temporary locations and executes shell commands including git, gh, and node.
  • Sanitization: The use of the --body-file flag for GitHub CLI commands avoids potential shell injection by passing content via files rather than command-line arguments.
  • [COMMAND_EXECUTION]: The skill executes multiple Git and GitHub CLI commands to manage pull requests.
  • Evidence: SKILL.md instructs the agent to run git status, git log, git rev-list, git diff, git push, gh pr create, gh pr edit, and gh pr view. It also runs a local script using node scripts/validate-pr-artifact.mjs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 06:02 AM