The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute infsh (inference.sh) CLI commands. These commands allow the agent to log in, run AI models for image generation (e.g., falai/flux-dev-lora), generate text-to-speech (e.g., falai/dia-tts), and post to social media (e.g., x/post-create). All commands are within the scope of the vendor's provided tools.
[EXTERNAL_DOWNLOADS]: The skill documentation references the installation of additional utility skills via npx skills add. These references point to the vendor's official repository (inference-sh/skills) and represent standard extension of the agent's capabilities within the vendor's ecosystem.
[PROMPT_INJECTION]: The skill is designed to ingest and process external content, such as blog posts and podcast transcripts, which presents a surface for indirect prompt injection. While malicious instructions could be embedded in the content being repurposed, this is a standard risk for content processing skills and is mitigated by the specific task-oriented instructions provided.

content-repurposing