customer-research
Warn
Audited by Snyk on Feb 15, 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 Research Process and "Tier 4 — External Sources" explicitly instruct the agent to perform web searches and consume community forums and third‑party documentation (public websites/user-generated content), so the agent will ingest untrusted external content as part of its workflow.
Audit Metadata