pr-comment-resolver

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and act upon untrusted data from external pull request comments, which creates a surface for indirect prompt injection.
  • Ingestion points: Pull request comments or code review feedback provided by users or external systems.
  • Boundary markers: None. The prompt instructs the agent to analyze the comment and implement the changes without specifying delimiters to separate instructions from data.
  • Capability inventory: While no scripts are provided, the instructions task the agent with implementing code changes (file writing) and verifying resolutions (potentially involving test execution tools).
  • Sanitization: The skill lacks any instructions to sanitize or validate the content of the comments before implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:10 PM