The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the infsh command-line interface to perform operations such as user authentication and executing remote applications for media generation and social media interaction.
[EXTERNAL_DOWNLOADS]: It references external skill packages and suggests installing additional dependencies from the inference-sh registry using the npx command.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted long-form content (e.g., blog posts, transcripts) and use the extracted information to drive downstream actions.
Ingestion points: Processes external source material such as blog posts, podcast transcripts, and video content (referenced in conversion recipes).
Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore instructions embedded within the source content.
Capability inventory: The skill allows the agent to post to social media (X/Twitter) and generate various media assets (images, video, audio) through external platform tools.
Sanitization: No sanitization or validation of the input content is performed before it is interpolated into prompts for media generation or social media posts.

content-repurposing