memory-fabric
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration specifies the use of the official
@anthropic/memory-mcp-servervia npx. This resource is provided by a recognized and trusted organization. - [PROMPT_INJECTION]: The skill facilitates the extraction of entities and relationships from natural language statements for storage in a knowledge graph. This is an indirect prompt injection surface typical for memory management systems.
- Ingestion points: Natural language input is processed in the extraction logic described in
references/entity-extraction.md. - Boundary markers: The instructions do not define explicit markers or delimiters for the ingested text.
- Capability inventory: The skill utilizes
mcp__memory__*tools for mutating and searching the knowledge graph. - Sanitization: No specific sanitization or filtering logic is provided for the extracted data before storage.
Audit Metadata