skills/xoai/sage/memory/Gen Agent Trust Hub

memory

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust mechanism for project knowledge persistence using a local fallback directory or specific MCP tools. The logic is transparently documented and follows best practices for maintaining context across sessions.\n- [PROMPT_INJECTION]: The skill maintains an attack surface for indirect prompt injection by retrieving context from memory stores that may contain untrusted data.\n
  • Ingestion points: Context is ingested via sage_memory_search results and by reading files within the .sage-memory/ directory (SKILL.md).\n
  • Boundary markers: Absent. There are no instructions for the agent to distinguish between its own logic and instructions that might be embedded within retrieved memory entries.\n
  • Capability inventory: The agent can read and write files to the project root and execute local memory management tools (SKILL.md).\n
  • Sanitization: The skill does not perform sanitization, validation, or escaping of memory content before it is interpolated into the agent's working context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 01:31 AM
Security Audit — agent-trust-hub — memory