explain-changes
Warn
Audited by Snyk on Nov 12, 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 only outsider-reachable path is the MCP tool-call route (e.g., email or Notion), where the agent must choose to call a tool and then saves that result as evidence, so outsider text is exposed only after the agent selects a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata