exam-creator-skill
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow includes “photographed handwritten pages, when provided” and an extraction pass that reads those user-provided images via multimodal vision/OCR, which can contain outsider-authored free text (e.g., teacher/other people’s handwriting) that is then ingested into the LLM context for drafting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata