Indices
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: 1.00). The skill explicitly fetches and scrapes arbitrary external websites (see the "website" parameter in mcp__indices-mcp__createTask and the "Retrieving data from external websites"/createRun workflow), so the agent will ingest untrusted public third-party content that could enable indirect prompt injection.
Audit Metadata