creature-design
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured design principles and validation checklists for creative tasks. No executable code (scripts, binaries), network operations (curl, wget, etc.), or attempts to access sensitive system files (e.g., .ssh, .env) were detected across the skill files or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided creature concepts. While it lacks explicit sanitization or boundary markers for user data, the risk is mitigated as the skill possesses no dangerous capabilities.
- Ingestion points: User-provided descriptions of creatures or monsters.
- Boundary markers: None present in the instructions.
- Capability inventory: No subprocess calls, file-write operations, or network requests are present in the instructions or references.
- Sanitization: No input filtering is implemented.
Audit Metadata