world-creation
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform cat operations on specific local files (e.g., world-code/voice.md) to retrieve context from previous steps in the 'World Code' framework. This is a functional requirement for state management.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8) because it incorporates data from local files into its internal logic. 1. Ingestion points: Reads from world-code/voice.md, world-code/climax.md, and world-code/method.md. 2. Boundary markers: None identified. 3. Capability inventory: Bash tool for file system reading and writing. 4. Sanitization: None.
Audit Metadata