azure-ai
Warn
Audited by Snyk on Nov 18, 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). The required workflow reads the user's own index schemas, query payloads, Speech logs, audio files, and Azure Monitor/Search diagnostics, and the only path that could surface outsider-authored text is the optional
azure__searchsearch_querycall returning documents from an index the agent selects to query, which is own-tenant data an outsider could only influence if it was previously indexed from external content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata