research-assistant
Warn
Audited by Snyk on Jun 30, 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 instructs the agent to “Proactively Make Web Searches” and include fetched documentation/links, so at runtime it may ingest outsider-authored free text from public web pages/articles into the LLM context via the web browsing/search retrieval path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata