mesh-memory

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill implements a semantic memory service via standard Model Context Protocol (MCP) tools.
  • [EXTERNAL_DOWNLOADS]: The skill documentation refers to the project repository at github.com/dklymentiev/mesh-memory for setup instructions.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by retrieving stored content into the agent context. 1. Ingestion points: Document content via mesh_add and mesh_update tools in SKILL.md. 2. Boundary markers: None identified in the skill instructions. 3. Capability inventory: CRUD and search operations on documents via a local PostgreSQL backend. 4. Sanitization: Not explicitly specified in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 10:59 AM
Security Audit — agent-trust-hub — mesh-memory