rw-api-reference
Warn
Audited by Snyk on Apr 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts and ingests arbitrary HTTPS asset URLs (see "URL Requirements" and the SDK examples using promptImage like "https://example.com/image.jpg") and allows attaching document/content to Avatars, meaning untrusted public web content can be read by the service and influence generation/agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata