research-assistant
Warn
Audited by Snyk on Jun 26, 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 runtime workflow includes “Search multiple sources” and “Gather information” via web search, which can fetch public web pages and ingest their body text into the agent’s LLM context (outsider-authored free text from arbitrary URLs/pages).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata