agent-stat
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to guide the user through a structured design process for AI agents. It does not exhibit malicious patterns such as credential harvesting, data exfiltration, or unauthorized command execution.
- [SAFE]: File system operations are scoped to the generation of markdown configuration files within the
.claude/agents/directory, which is the intended behavior for defining sub-agents in supported environments. - [SAFE]: No external dependencies, remote script downloads, or dynamic execution of untrusted code were identified. The skill operates using static templates and reference maps provided within its own package.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a template generator that interpolates user-provided text into configuration files. While this creates a surface where a user could manually insert malicious instructions into their own agent definitions, the skill provides a highly structured framework (Role-Trait-Policy) that encourages safe, deterministic behavior and includes guidelines for resolving policy conflicts with a priority on safety.
Audit Metadata