agent-standards
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown files defining cognitive standards for AI agents. It does not include any executable scripts, binary files, or tool definitions that pose a runtime risk.- [SAFE]: The instructions incorporate mandatory security protocols, such as the 'Memory Gate' which requires agents to scrub secrets and PII before persisting data to long-term memory.- [SAFE]: The skill provides defensive context engineering guidelines, such as excluding sensitive directories and using structured context packing to maintain clear boundaries between data inputs and agent reasoning.
Audit Metadata