heygen-avatars
Warn
Audited by Snyk on Feb 15, 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 downloads arbitrary external URLs in rules/assets.md ("Uploading from URL" uses fetch(sourceUrl) to pull a file and then upload it), so the agent can ingest untrusted third-party content from arbitrary URLs as part of its workflow.
Audit Metadata