tanstack-ai-memory-mem0
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation describes a memory retrieval process where data from an external server is rendered directly into the agent's system prompt. This constitutes a potential surface for indirect prompt injection if the stored data contains malicious instructions.\n
- Ingestion points: Data enters the context via the
/searchendpoint of a mem0 server specified by thebaseUrl.\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands within the retrieved memory content.\n
- Capability inventory: The middleware manages memory turns; no dangerous file system or command line capabilities are exposed directly in the provided setup.\n
- Sanitization: There is no mention of sanitizing, validating, or escaping the retrieved memory content before it is interpolated into the prompt.\n- [EXTERNAL_DOWNLOADS]: The skill setup utilizes the
@tanstack/ai-memoryand@tanstack/ai-memory/mem0Node.js packages. These are official resources associated with the skill's authoring vendor.
Audit Metadata