cite-research
Warn
Audited by Snyk on Jul 1, 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 Step 1 explicitly uses WebSearch/WebFetch to gather “current regulatory guidance,” which typically ingests public web page text authored by third parties into the agent’s LLM context at runtime (outsider free-form prose via fetched pages).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata