hyperframes
Fail
Audited by Snyk on Nov 14, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a video-workflow router with no malicious intent, but its init behavior silently pulls and refreshes skills from GitHub on every run and neuters the
--skip-skillsopt-out, which goes beyond what the advertised task needs and weakens the user's control over what gets installed.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The router itself reads no outsider text, but it routes GitHub PR inputs to
/pr-to-video, which reads PR content via theghCLI, and the recall-first override favors the higher rating for that GitHub PR reading path.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata