ai-podcast
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a legitimate multi-step process for media creation using authorized platform tools. No malicious behavior or intent was detected during the analysis.
- [COMMAND_EXECUTION]: The skill utilizes the
infsh app runcommand structure to execute various AI generation tasks such aspruna/p-image,inworld/text-to-speech-2, andphota/train. These commands are specific to the vendor's platform ecosystem and are used as intended for the skill's primary purpose. - [DATA_EXFILTRATION]: No sensitive file access (such as searching for credentials, tokens, or SSH keys) or unauthorized data transmission to external, non-whitelisted domains was detected. Use of URLs in command arguments is for processing user-supplied media.
- [PROMPT_INJECTION]: The instructions do not contain any patterns suggesting an attempt to bypass safety filters, override system prompts, or manipulate the agent's behavior beyond the operational scope of the video generation pipeline.
Audit Metadata