ai-podcast

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute infsh app run commands. This is the intended method for interacting with the various media generation apps (pruna, phota, inworld) and the media-merger utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a pipeline for processing external data such as image URLs and script text.
  • Ingestion points: Character image URLs in phota/train and script content in inworld/text-to-speech-2 within SKILL.md.
  • Boundary markers: The skill does not define specific delimiters to separate untrusted data from instructions when passing them to the sub-apps.
  • Capability inventory: The skill possesses the ability to execute shell commands and read/write files via the Bash, Read, and Write tools.
  • Sanitization: There is no evidence of input validation or content filtering for the data processed by the pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — ai-podcast