skills/chujianyun/awesome-gpt-image2-ppt-skills/red-white-corporate-training-ppt/Gen Agent Trust Hub
red-white-corporate-training-ppt
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely as a set of instructions for the AI agent to generate image prompts. It does not include any executable code, shell scripts, or external dependencies. All tool invocations refer to internal image generation capabilities.
- [PROMPT_INJECTION]: The skill identifies as having an indirect prompt injection surface because it processes untrusted user-supplied content (titles, themes, and module descriptions) and interpolates them directly into a prompt template for the
image_gentool. This is a low-risk architectural observation rather than a malicious finding. - Ingestion points: User input for '主题' (Theme), '主标题' (Main Title), and '主要内容' (Main Content) in
SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are used to wrap the interpolated user content.
- Capability inventory: The skill's primary capability is limited to invoking the
image_gentool. - Sanitization: No input validation or sanitization is performed on user content before processing.
Audit Metadata