media-use
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow searches external catalogs (Openverse for sound effects, per
audio/references/sfx.md, and HeyGen's music catalog for BGM, peraudio/references/bgm.md), so outsider-authored titles and creator metadata reach the agent only after it actively queries and selects results, which is a low-risk path.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill makes operational changes:
heygen-voice.mjs deleteremoves a voice clone from the HeyGen account, andauth loginand.hyperframes/credit-limit.jsonwrite persistent credential and configuration state. The evidence does not establish explicit irreversible operational loss, since a deleted clone can be re-created from its source recording and the loss is of user content rather than operational infrastructure, so the answer is low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata