The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and process untrusted user content (e.g., blog posts, podcast transcripts) into derivative social media formats.
Ingestion points: User-provided long-form content is transformed using instructions defined in the Conversion Recipes section.
Boundary markers: Absent; the instructions do not define delimiters or specific safety boundaries for isolating input data from processing logic.
Capability inventory: The skill has the capability to generate images, video, and audio, and post to X (Twitter) via the infsh tool.
Sanitization: None; user-supplied text is used directly in prompts for transformation and posting.
[COMMAND_EXECUTION]: Employs the infsh CLI tool via the Bash tool to execute functions like authentication, media generation, and social media management.
[EXTERNAL_DOWNLOADS]: References installation scripts and additional skill dependencies hosted on the vendor's official GitHub repository and via the npx package runner.

content-repurposing