gpt-image-slide-plan
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional, focused on organizing presentation content into a logical narrative structure. It does not utilize any tools, scripts, or external network resources.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided data (prompts and files) to generate its output. While this creates an ingestion surface, the risk is negligible as the skill lacks any dangerous capabilities such as file system writing, command execution, or network access.
- Ingestion points: The skill processes DESIGN.md, user-uploaded files, and objective prompts.
- Boundary markers: No delimiters or safety instructions are used to separate untrusted data.
- Capability inventory: None. The skill does not request any tools or use shell/network commands.
- Sanitization: No input sanitization is implemented.
Audit Metadata