Convex Agents Threads

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill provides an interface for passing user-provided prompts to an AI generation tool, which is a standard part of its conversational management functionality. Although no specific sanitization or boundary markers are shown in the snippets, the usage is consistent with the skill's primary purpose. 1. Ingestion points: 'prompt' parameter in the 'continueConversation' action handler. 2. Boundary markers: Absent in code snippets. 3. Capability inventory: AI text generation via 'thread.generateText'. 4. Sanitization: Absent in code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM