planning-prompts
Warn
Audited by Snyk on Mar 22, 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's research workflow (reference/meta-prompts.md "Research Prompts" template) explicitly instructs using WebFetch/WebSearch with external URLs and search queries to ingest public web content for findings that feed into plans and automated Do prompts, so untrusted third-party pages could influence subsequent agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata