tanstack-ai-memory-mem0
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a memory recall mechanism that interpolates data from an external server into the system prompt, creating a vector for indirect prompt injection.\n
- Ingestion points: Untrusted data enters the agent context from the mem0
/searchendpoint via therecallfunction described inSKILL.md.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation for the recall output.\n
- Capability inventory: The skill is configured to use network operations to reach a server specified by the
MEM0_URLenvironment variable orlocalhost.\n - Sanitization: No data sanitization or validation of the retrieved memory strings is specified in the skill definition.
Audit Metadata