extract-tables
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). In the required runtime path
read_pdf()→ “Shadow-LEGO Strategy Routing” (/assistant classify(task="table-strategy-router")) the skill sends extracted feature text (derived from the user-provided PDF) into the assistant as model input, but it does not ingest any outsider-authored free-text channel directly like emails/chat/inbox/issue bodies.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata