multiplayer-game
Warn
Audited by Snyk on Apr 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's required BASE_SKILL.md includes a "Workflows" example (processTask(url) in the workflow loop) that fetches arbitrary URLs supplied in queue messages (and the AI/user-generated-actors guide describes deploying/executing user-generated code), so following the mandated workflow the agent would ingest and act on untrusted third-party content from arbitrary URLs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata