japanese-lesson
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 requires and reads public podcast and YouTube transcripts (the required "*_linked.txt" with YouTube URLs and timestamps and the plain transcript files) — user-generated, public content the agent will ingest and interpret as part of its workflow, enabling indirect prompt injection.
Audit Metadata