ship-learn-next
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to "Read the provided file (transcript, article, notes)" via a user-provided FILE_PATH and specifically mentions YouTube transcripts, articles, and course notes, so it ingests and interprets arbitrary public/user-generated third-party content.
Audit Metadata