pull-request

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local command-line interfaces to interact with the version control system and GitHub.
  • Evidence: SKILL.md defines a workflow using git diff, git push, and gh pr create to automate pull request creation.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and summarizes code changes that may contain malicious instructions.
  • Ingestion points: Data entering the agent context via the git diff develop..HEAD command in SKILL.md.
  • Boundary markers: Absent; there are no instructions to the agent to distinguish between the diff data and its own system instructions.
  • Capability inventory: The skill has the ability to push data to remote repositories and create pull requests on GitHub (git push and gh pr create in SKILL.md).
  • Sanitization: Absent; the code changes are processed directly without validation or escaping to prevent embedded instructions from influencing the summary output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:16 AM