memos-cloud-server

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits conversation messages and queries to the official MemOS API (memos.memtensor.cn). This data transfer is the intended function of the memory service and is performed over an authorized connection using a user-provided API key.
  • [PROMPT_INJECTION]: The agent is instructed to use retrieved memory context to inform its answers. While this creates a pathway for external data to enter the prompt context, the skill is limited to memory management and does not possess capabilities that would allow for system compromise.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:39 PM