auto
Warn
Audited by Snyk on Jul 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). /ork:auto ingests the outsider-authored “goal in plain English” provided by the user at runtime to classify/confirm and then hand off to specialist skills, so prompt-injection text submitted by an outsider directly enters the router’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata