talking-head-production
Warn
Audited by Snyk on Aug 6, 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). SKILL.md describes a CLI workflow where outsider-supplied JSON fields like
voice_script/promptare passed to inference.sh apps (e.g.,pruna/p-video-avatar,pruna/p-image) without any required prior selection/filtering step inside the workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata