The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute infsh app run commands, which is the standard mechanism for orchestrating the various AI services (such as image generation, speech synthesis, and video merging) required for its functionality.
[EXTERNAL_DOWNLOADS]: The skill interacts with several external AI services (e.g., pruna, phota, inworld, google) via a command-line interface to process media. These interactions are core to the skill's purpose and are documented as standard operating procedures.
[PROMPT_INJECTION]: The instructions contain several behavioral rules (e.g., 'NEVER run p-video-avatar clips in parallel', 'ALWAYS QA frames') aimed at ensuring output quality and resource efficiency. These are benign instructional constraints and do not attempt to bypass safety filters or override agent autonomy in a malicious way.
[SAFE]: No evidence of obfuscation, hardcoded credentials, unauthorized file access, or persistence mechanisms was found during the analysis of the skill's instructions and commands.

ai-podcast