mimir-memory

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to run npx memory-mimir, which downloads and executes code from the npm registry. This package is identified as a legitimate vendor resource for the author 'triplewhite'.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8).\n
  • Ingestion points: Data enters the system via the mimir_store tool which saves facts and preferences provided by the user.\n
  • Boundary markers: Memories are delimited by <memories> tags when injected into the agent's context window.\n
  • Capability inventory: The skill possesses the ability to perform deep memory searches, store new facts, and delete existing entries.\n
  • Sanitization: No explicit sanitization or filtering of the stored 'memory' content is described, meaning instructions embedded in stored data could influence the agent during auto-recall.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 03:33 PM