trans
Warn
Audited by Snyk on Aug 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The runtime workflow executes a local script (
scripts/look_tongji.py) to transcribe a specified lecture fromlook.tongji.edu.cnbased on user-supplied URL/IDs, meaning outsider-authored lecture content is fetched and ingested as text at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata