skills/mem0ai/mem0/mem0-remember/Gen Agent Trust Hub

mem0-remember

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [SAFE]: The skill utilizes vendor-specific tools add_memory and get_event_status to perform its primary function of memory management. This is consistent with the skill's stated purpose and authored context.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes user-provided text for storage.
  • Ingestion points: User input captured via the /mem0-remember command in SKILL.md.
  • Boundary markers: Absent; the text is passed directly to the storage tool.
  • Capability inventory: add_memory, get_event_status.
  • Sanitization: None specified, though the content is stored verbatim (infer=False) and not executed, mitigating potential risks.
  • [DATA_EXFILTRATION]: The skill transmits user text and project metadata to the mem0 service.
  • Evidence: Calls add_memory with user input and project identifiers.
  • Context: This is the core intended functionality of the skill and is directed to the vendor's own infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:54 AM
Security Audit — agent-trust-hub — mem0-remember