gpt-image-slide-render
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from
DESIGN.mdand a JSON file to determine image generation and file naming. - Ingestion points:
DESIGN.mdandslide_prompts.jsonin the current project. - Boundary markers: None present.
- Capability inventory: File reading, native image generation tool usage, and file writing (copying/saving images to the workspace).
- Sanitization: No explicit sanitization or filtering of input content is described.
- [NO_CODE]: The skill consists entirely of natural language instructions for the agent and does not include any accompanying scripts, executables, or package manifests.
Audit Metadata