Convex Agents Messages

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: 0.80). The skill saves, retrieves, and displays arbitrary user-generated messages (e.g., via saveMessage and listUIMessages and rendering message.text in the UI), so the agent will ingest untrusted third-party content from conversation threads that could carry indirect prompt-injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:20 AM