agent-memory-discipline

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text providing guidelines for an agent's logic when interacting with memory tools. It does not include or execute any code.
  • [DATA_EXPOSURE]: The instructions explicitly include a security best practice, directing the agent not to save secrets, tokens, or personal data to its persistent memory backend.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a mitigation strategy for potential indirect prompt injection by instructing the agent to surface contradictions found in memory to the user rather than silently resolving them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 12:09 AM
Security Audit — agent-trust-hub — agent-memory-discipline