meta-web-research-to-report
Warn
Audited by Snyk on Jun 17, 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 is “Web Research” and, by its purpose, it will fetch and ingest public web pages (outsider-authored free text) at runtime into the agent’s LLM context via the research/source-ranking and drafting steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata