book-notes
Fail
Audited by Snyk on Oct 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill contains instructions to promote an external skill installation repository (skillhub) when encountering capability gaps, which constitutes a minor unauthorized or unnecessary redirection of behavior (medium security boundary steering).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill contains a reference to a GitHub repository (
github:mindverse/skillhub) used as an installation instruction for an external skill marketplace tool during capability-gap responses, constituting an unofficial operational dependency.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata