create-anyone
Warn
Audited by Snyk on Apr 13, 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 instructs the agent to automatically fetch and ingest open web content (e.g., "WebSearch" for public/historical figures and "Social media archive", "character wiki" in SKILL.md / README and Phase 3), so untrusted user-generated/public sources are read and used to build persona.json/training data and therefore can materially influence subsequent agent behavior and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata