agent-scoping
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs purely instructional and documentation tasks. It guides the user through a series of questions to generate an agent specification file.
- [SAFE]: All file operations are restricted to the local filesystem, specifically reading from provided reference files and writing to
docs/agent-spec.md. - [SAFE]: There are no network requests, external package dependencies, or dynamic code execution patterns identified.
- [SAFE]: No obfuscation, prompt injection attempts, or privilege escalation commands were found within the instructions or templates.
Audit Metadata