pr-review-responder

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a tool, fetch_pr_comments, which ingests untrusted data from external sources (GitHub Pull Request comments). This creates a vulnerability to indirect prompt injection, where malicious instructions embedded in comments could influence the agent's behavior during a review session.
  • Ingestion points: External content is retrieved via the fetch_pr_comments script in manifest.json.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands within the fetched data are defined in the skill documentation.
  • Capability inventory: The tools are defined as readonly, but the resulting output is returned to the agent's context for processing and response generation.
  • Sanitization: No sanitization, filtering, or validation logic for the fetched comment text is documented in the skill metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 09:11 PM
Security Audit — agent-trust-hub — pr-review-responder