The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute infsh CLI commands. This is the primary method for interacting with the inference.sh platform to run AI models for image, video, and text generation.
[EXTERNAL_DOWNLOADS]: The skill references an external installation guide at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md for the required infsh CLI. It also suggests extending capabilities by adding other skills from the inference-sh organization using npx.
[DATA_EXFILTRATION]: The skill includes functionality to post content to external social media platforms, specifically demonstrated with the x/post-create application for Twitter/X. This is an intended feature for content distribution.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user content (such as blog posts and podcast transcripts) to generate social media outputs.
Ingestion points: User-provided source content like blog posts, podcast transcripts, and video descriptions processed in the conversion recipes in SKILL.md.
Boundary markers: Absent; the instructions do not include delimiters or specific warnings for the agent to ignore instructions embedded within the source content.
Capability inventory: The skill uses the Bash tool to execute infsh app run commands, which can generate AI content and post directly to social media platforms.
Sanitization: None; there are no documented steps for validating or escaping external content before it is interpolated into model prompts or passed to the CLI.

content-repurposing