memory-integration

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Data Exposure (SAFE): The skill accesses historical conversation data and knowledge graphs. This is the intended functionality for cross-session continuity and does not involve unauthorized access to sensitive system files or private credentials.
  • Indirect Prompt Injection (SAFE): Ingesting historical conversation data and graph entries presents a potential surface for indirect prompt injection. However, this is an inherent property of memory-integration skills and is handled here using structured tool calls rather than unsafe interpolation.
  • Dependency and Execution Analysis (SAFE): No external dependencies, remote script downloads, or dynamic code execution patterns (like eval or exec) were identified. The skill relies on predefined MCP tools for its operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:00 PM