ai-podcast
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches character reference images from external URLs provided by the user during the training and image generation processes (Step 1).
- [COMMAND_EXECUTION]: The skill utilizes the
infsh app runinterface to execute several specialized AI applications, includingpruna/p-image,phota/train, andinfsh/media-merger, to perform media processing and video assembly. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing user-provided content that influences downstream outputs.
- Ingestion points: User-supplied image URLs and conversational script text are ingested for use in Steps 1, 5, and 6.
- Boundary markers: There are no explicit delimiters or protective instructions used to isolate user data within the JSON payloads passed to the tools.
- Capability inventory: The skill invokes multiple external AI services via the
infshCLI to generate and merge media files. - Sanitization: The input content is not sanitized or validated before being interpolated into parameters for the AI generation tools.
Audit Metadata