convex-agent
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of a backend that processes message history and vector search results (RAG). This introduces an attack surface where malicious content in retrieved documents or user messages could influence the agent's behavior.
- Ingestion points: The skill handles durable threads, message history, and retrieved vector search results as specified in
SKILL.md. - Boundary markers: The instructions do not explicitly mandate the use of delimiters or warnings to ignore embedded instructions in the ingested data.
- Capability inventory: The agent backend supports tool-calling, model execution, and vector retrieval.
- Sanitization: No specific sanitization or filtering logic for external content is described in the setup workflow.
Audit Metadata