gemini-consultation
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill accepts and analyzes user-supplied documents and images via the --file argument (e.g., PDFs/images), which are arbitrary untrusted third-party content the agent will read and interpret, enabling indirect prompt injection.
Audit Metadata