ce-ideate
Warn
Audited by Snyk on May 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: 0.90). The skill explicitly runs always-on web research (see "Web Research (V5, V15)" and Phase 1), dispatching a ce-web-researcher to fetch and ingest public web content and user-supplied URLs whose results are merged into the grounding summary and used to drive ideation and decision-making, so untrusted third-party pages could materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata