The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the belt CLI to run various applications for tasks like image generation, text-to-speech, and social media posting. The execution environment restricts Bash to commands starting with belt, but these operations involve remote service interaction and processing of user data.
[EXTERNAL_DOWNLOADS]: The skill instructions guide users to install the belt CLI and related skills using npx commands and provides a link to an external installation script on GitHub (raw.githubusercontent.com/inference-sh/skills/main/cli-install.md).
[INDIRECT_PROMPT_INJECTION]: The skill processes external content such as blog posts, podcast transcripts, and videos, presenting a risk of indirect prompt injection.
Ingestion points: The skill ingests external data for repurposing, including blog text and podcast audio.
Boundary markers: The instructions do not define boundary markers or safety delimiters for the content being processed.
Capability inventory: The skill has the capability to post to external social media platforms and run remote AI models via the belt CLI.
Sanitization: No sanitization or filtering methods for incoming content are specified in the provided instructions.

content-repurposing