walkthrough-pr

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and deeply analyze pull request diffs and file content obtained via gh pr diff and git diff to determine the logic flow.
  • Ingestion points: Diff content and file source code fetched from external pull requests or local branches as described in the Procedure section of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or system-level directives to ignore instructions that might be embedded within the code or comments of the PR being reviewed.
  • Capability inventory: The agent uses gh (GitHub CLI) and git tools to read repository data and interacts with the user to explain changes.
  • Sanitization: No validation or sanitization is performed on the diff text before the agent is instructed to "read enough of the diff to understand what the change actually does end-to-end", which could allow malicious code comments to influence agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 04:17 PM
Security Audit — agent-trust-hub — walkthrough-pr