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_memorytool 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_memorycall template. - Capability inventory:
add_memoryandget_event_statustools. - Sanitization: No explicit sanitization of input text is defined before storage.
Audit Metadata