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

remember

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text and interpolates it directly into the add_memory tool call. While this creates an ingestion surface for untrusted data, it is the primary function of the skill and does not include execution-capable scripts that could be exploited via this channel.
  • Ingestion points: User input via the /mem0:remember <text> command.
  • Boundary markers: None present in the add_memory call template.
  • Capability inventory: add_memory and get_event_status tools.
  • Sanitization: No explicit sanitization of input text is defined before storage.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 07:27 AM
Security Audit — agent-trust-hub — remember