GordenImagePPTGen
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and content to generate presentation outlines and image prompts, which represents an attack surface for indirect prompt injection.
- Ingestion points: User-provided topics and content enter the agent's context in the outline and prompt generation phases.
- Boundary markers: Instructions emphasize using verbatim content from the user, but explicit structural delimiters for untrusted input are not defined.
- Capability inventory: The skill uses a local Python script (
scripts/compose_pptx.py) to create PPTX files and process images. It does not perform network operations or execute arbitrary shell commands. - Sanitization: No specific sanitization or escaping of user-provided content is implemented before interpolation into image generation prompts.
Audit Metadata