Skills
skills/warpdotdev/common-skills/review-pr/Gen Agent Trust Hub

review-pr

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted input from pull request artifacts, which is a surface for indirect prompt injection. This is an inherent risk of the tool's core functionality and is mitigated by its restricted execution environment.
  • Ingestion points: pr_diff.txt and pr_description.txt mentioned in the SKILL.md context.
  • Boundary markers: None identified in the prompt template.
  • Capability inventory: The skill is limited to writing a local file (review.json) and executing a JSON validator (jq).
  • Sanitization: No input sanitization is specified for the diff or description content.
  • [COMMAND_EXECUTION]: The instructions include a step to validate the generated JSON using the jq command-line utility, which is a benign and standard software development task.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 07:37 PM