The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from various social platforms and newsletters which could contain malicious instructions.- Ingestion points: External source content (blogs, X threads, LinkedIn posts) is ingested as the primary input for repurposing in step 1.- Boundary markers: The skill does not define specific delimiters to isolate user-provided content from the agent's instructions, though it does strip platform-specific artifacts.- Capability inventory: The skill utilizes a publishing function lib.publish and hands off data to other content-generation skills (yt-community-post-writer, yt-title-optimizer, etc.).- Sanitization: The workflow incorporates a mandatory human 'Approval card' (step 8) and the publishing tool is designed to return a copy-paste block rather than execute automated actions, providing a strong security boundary.

yt-repurposer