chat-room

Warn

Audited by Snyk on Aug 2, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). reference/actors/debugging.md describes Rivet Engine inspector endpoints (e.g., /inspector/workflow-history, /inspector/queue?limit=10, /inspector/database/rows) that expose runtime workflow history, queue messages, and database row text to external callers via HTTP, so outsider-authored free text present in those monitored artifacts can be ingested by an AI agent using the debugger/inspector workflow.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 2, 2026, 12:07 AM
Issues
1
Security Audit — snyk — chat-room