draft-validation
Warn
Audited by Snyk on Nov 15, 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). DraftValidation and EditValidation send a DataScan summary of the user-supplied table, including sample string values, to the LLM at runtime, so any outsider-written text stored in that table could reach the model; the agent does not search for or fetch this content, and the table is the user's own data, so this is a low-risk ambiguous case.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata