distill-memory
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the nmem CLI tool to store conversation highlights. It provides specific syntax for adding and updating memories with flags for unit-type, labels, and importance.
- [SAFE]: The skill behavior is consistent with its purpose of memory distillation. No indicators of prompt injection, obfuscation, or persistence were found. External links point to documentation associated with the vendor's domain.
- [SAFE]: Indirect prompt injection surface analysis: (1) Ingestion points: Conversation context and breakthrough moments. (2) Boundary markers: Absent from the prompt instructions. (3) Capability inventory: CLI execution of nmem. (4) Sanitization: Not explicitly defined in the skill instructions. The surface is utilized for legitimate memory storage.
Audit Metadata