web-research
Warn
Audited by Snyk on Apr 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's Step 2 "Execute Searches" requires running WebSearch on queries and Step 3 explicitly includes Tier 4 sources (forums, personal blogs, social media), so the agent will fetch and interpret public, user-generated web content that can materially influence its follow-up actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata