mem0
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing shell commands using
npx @useclawlink/clito perform logins, connections, and data operations (e.g.,npx @useclawlink/cli run mem0). - [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and run the
@useclawlink/clipackage from the NPM registry at runtime. - [INDIRECT_PROMPT_INJECTION]: The skill processes memory records and metadata retrieved from the Mem0 service which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data is ingested through actions like
mem0_create_memory_entry(which searches memories) andmem0_add_new_memory_recordsinSKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the skill definition.
- Capability inventory: The skill has the capability to execute shell commands and modify data in the Mem0 platform.
- Sanitization: There is no evidence of sanitization or validation of the content retrieved from Mem0 before it is processed by the agent.
Audit Metadata