mage-video-remake
Fail
Audited by Snyk on Nov 13, 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 legitimate remake workflow, but its instruction to never tell the user which outside model made the original withholds information from the user, a sketchy concealment that is not clearly malicious.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow runs rea-video on a user-selected video file and ingests its on-screen captions and transcribed speech, which are outsider-authored text, but the agent only reads it after the user picks that specific item, so exposure is low rather than medium.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The decisive dependency is the pinned
pipx installof rea-video's source from an individually owned GitHub repository, which is installed and executed; the commit hash fixes the content but does not independently authenticate the publisher, so it is unofficial and reputable, giving medium.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata