api-reference

Warn

Audited by Snyk on Mar 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly accepts and ingests arbitrary HTTPS asset URLs (e.g., promptImage/referenceImage) and user-created documents via POST /v1/documents which can be linked to an Avatar (Documents and Characters/Avatars sections), meaning untrusted third‑party content is read and used as knowledge/inputs that can influence generation and avatar behavior, enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 25, 2026, 12:14 AM
Issues
1