claude-agent-design
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown documentation and YAML configuration files providing structural guidance for agent design. No scripts, binaries, or automated tasks are included.
- [SAFE]: No network activity, remote downloads, or external dependencies are defined. All references point to local files within the skill package.
- [SAFE]: There are no indicators of prompt injection, obfuscation, or persistence mechanisms. The content is transparent and focused on architectural safety patterns.
- [SAFE]: While the skill analyzes 'agent orchestration specs' (Category 8 surface), it lacks any functional capabilities (such as shell execution or file writing) that could be exploited via indirect injection.
Audit Metadata