The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (e.g., blog posts, podcast transcripts) to generate derivative assets. This creates a surface for instructions embedded in the data to hijack the agent's behavior during the transformation process.
Ingestion points: Long-form source content provided by the user in SKILL.md templates for blog-to-thread and blog-to-social conversions.
Boundary markers: Absent. The templates do not use clear delimiters or specific instructions to the agent to disregard commands found within the source material.
Capability inventory: The skill utilizes the belt CLI to generate images, audio, video, and notably to create social media posts via x/post-create.
Sanitization: No sanitization or validation logic is present to filter malicious commands from the source text before it is processed by the AI.
[EXTERNAL_DOWNLOADS]: The documentation references external resources and installation scripts.
Evidence: Provides a link to installation instructions hosted at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
Evidence: Recommends installing the belt-sh/cli and other related skills using the npx skills add command.

content-repurposing