mem0-search
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves content from an external memory database through the
search_memoriesandget_memorytools. - Ingestion points: Content is pulled from the Mem0 database based on user queries or memory IDs (SKILL.md).
- Boundary markers: Absent. There are no instructions for the agent to treat the memory content as untrusted data or to ignore any embedded instructions within the memory text.
- Capability inventory: The skill utilizes search and retrieval tools but does not have dangerous capabilities like file writing, network exfiltration, or shell execution.
- Sanitization: Absent. The memory content is formatted and displayed to the user without filtering for potential prompt injection patterns.
Audit Metadata