seed-concept-search
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 required workflow explicitly performs runtime web search (“brave-search”) and then returns “ranked list of candidate seed concepts with source references,” which implies the agent ingests outsider-authored free-form web page text into the LLM context for summarization/ranking.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata