Skills
Navigate
skills/pydantic/pydantic-ai-harness/pushing-commits-to-the-repo/Gen Agent Trust Hub

pushing-commits-to-the-repo

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and respond to Pull Request comments from both humans and bots.
  • Ingestion points: Instructions in SKILL.md direct the agent to "Triage every comment (bots and humans alike)" and poll for maintainer replies every 30 minutes.
  • Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate untrusted comment data from the agent's internal instructions.
  • Capability inventory: The skill uses gh (GitHub CLI) commands in SKILL.md to list labels (gh label list) and edit Pull Requests (gh pr edit), and implicitly uses git to push commits.
  • Sanitization: There is no mention of sanitizing or filtering the content of the comments before the agent processes them or incorporates them into its reasoning loop.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to perform repository management tasks.
  • Evidence: SKILL.md includes commands for gh label list --limit 100 and gh pr edit <number> --add-label <label>.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 11:18 PM