deepresearch-defense-standard
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s workflow explicitly performs runtime web research (e.g., “Search the web for the latest information” and “Prefer primary… sources”), which can ingest outsider-authored free text from fetched public pages/articles into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata