distill-memory
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the nmem CLI tool (commands: nmem m add, nmem m update) to interact with a knowledge base and persist conversation insights.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and storing conversation data that could contain malicious instructions.\n
- Ingestion points: Processes durable facts, decisions, and context from the conversation history as described in SKILL.md.\n
- Boundary markers: None specified to delimit or sanitize the content being stored.\n
- Capability inventory: Executes CLI commands via nmem for data persistence.\n
- Sanitization: No evidence of validation or sanitization for conversation content before it is passed to the storage tool.
Audit Metadata