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 run interface to execute several specialized AI applications, including pruna/p-image, phota/train, and infsh/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 infsh CLI 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
Risk Level
SAFE
Analyzed
Jun 19, 2026, 11:44 AM
Security Audit — agent-trust-hub — ai-podcast