andrew-ng
Warn
Audited by Snyk on May 3, 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). Yes — SKILL.md's "Agentic Workflow Iteration" explicitly instructs the agent to "perform web research to fetch context" (and AGENTS.md/frameworks reiterates this), meaning the agent will fetch and interpret open/public web content (e.g., the listed YouTube/blog sources) that could contain untrusted, user-generated instructions capable of influencing subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata