creator-character-designer
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which could contain malicious instructions.
- Ingestion points: The skill reads external content from
project/screenplay/character-brief.md,project/continuity/creator-director-vision.md, and various files inproject/production-design/to inform its design process. - Boundary markers: No explicit delimiters or instructions are defined to separate ingested data from agent instructions, which could lead to the agent following instructions embedded in a screenplay.
- Capability inventory: The skill has the capability to write files to the local
project/characters/directory and generate prompts for image generation tools like GPT Image 2.0. It does not possess capabilities for network exfiltration or shell command execution. - Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the data ingested from the screenplay or continuity files.
Audit Metadata