nowledge-mem

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides specific instructions for using the bash tool to execute nmem CLI commands (e.g., search, add, show) for memory management as a fallback mechanism.
  • [PROMPT_INJECTION]: The skill retrieves and processes data from an external memory store, which creates a surface for indirect prompt injection from historical thread content. Ingestion points: Data from nowledge_mem_query, nowledge_mem_search, and nmem CLI search outputs. Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions for retrieved content. Capability inventory: The skill has access to shell execution (bash) and memory operations. Sanitization: No sanitization of the retrieved data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 06:41 AM
Security Audit — agent-trust-hub — nowledge-mem