mcp-memory-recall

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill implements a pattern for ingesting untrusted data from an external memory source.
  • Ingestion points: The skill explicitly queries an external MCP/Neo4j memory server for project nodes, decisions, and constraints in SKILL.md.
  • Boundary markers: Absent. There are no instructions to the agent to treat retrieved memory strictly as data or to ignore instructions embedded within that memory.
  • Capability inventory: The skill uses MCP(*) which allows it to invoke any tool available on the configured MCP server, increasing the potential impact of an injection.
  • Sanitization: Absent. The skill does not define any logic to sanitize or validate the content retrieved from the database before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 11:21 AM