build-cognitive-context
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides a methodology for 'Context Engineering'. It guides the agent on how to manage context levels, resolve documentation conflicts, and document project-specific conventions.
- [SAFE]: No external network operations, remote script executions, or sensitive data access patterns were detected. The skill interacts primarily with standard project documentation files like
AGENTS.md,CANON.md, and local specification files. - [SAFE]: There are no indicators of prompt injection, obfuscation, or persistence mechanisms. The instructions reinforce safety and accuracy by requiring the agent to stop and clarify ambiguities with the human user rather than making assumptions.
Audit Metadata