quality-loop
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's Phase 1 "Source Compilation" explicitly calls for "External research
- Web search for biography, facts, external validation" and inclusion of "Sources for Verification" with URLs, meaning the agent will fetch and read arbitrary public web content/URLs as part of its workflow, exposing it to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata