neo4j-agent-memory-skill
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data, such as user messages and entity facts, into a knowledge graph to serve as agent memory.
- Ingestion points: Identified in SKILL.md within the MemoryClient API methods (e.g., add_message, add_entity) and several MCP tools (e.g., memory_store_message, memory_add_entity).
- Boundary markers: The instructions do not define specific boundary markers or instructions to ignore potential commands embedded within the processed memory data.
- Capability inventory: The skill enables agents to perform database read/write operations and exposes memory management tools to other compatible assistants.
- Sanitization: The documentation does not outline specific sanitization or validation routines for the content being stored in the memory graph.
Audit Metadata