behavioral-modes
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of behavioral instructions and persona definitions designed to improve AI performance and output consistency across different task types.- [SAFE]: The skill includes a 'SHIP' mode checklist that enforces security best practices, specifically instructing the agent to verify the absence of exposed secrets and the presence of input validation before deployment.- [SAFE]: The skill restricts tool access to standard, read-only file system tools ('Read', 'Glob', 'Grep') via the YAML frontmatter, providing a limited and safe execution environment.- [SAFE]: Multi-agent collaboration patterns (Explore, PEC, Mental Model Sync) are described as conceptual workflows and do not contain executable code or mechanisms for data exfiltration.
Audit Metadata