understand-memory-sync
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the
.understand-anything/knowledge-graph.jsonfile to create entities and relations in the Memory MCP server. This ingestion of local project data serves as a surface for indirect prompt injection. - Ingestion points: The skill reads the
.understand-anything/knowledge-graph.jsonfile from the project directory. - Boundary markers: None identified; there are no instructions to the agent to treat the ingested JSON data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill uses
mcp__memory__create_entities,mcp__memory__create_relations, andmcp__memory__add_observationsto persist data into long-term memory. - Sanitization: No sanitization, validation, or filtering of the knowledge graph content is specified before it is stored in the memory server.
Audit Metadata