The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from blog posts, podcasts, and videos to generate derivative content.
Ingestion points: Processes external files such as episode-42.mp3 and implied blog text content via various AI applications.
Boundary markers: The provided templates and prompts do not include explicit boundary markers or instructions to ignore potential commands embedded within the source content.
Capability inventory: The skill uses the belt CLI to interact with applications that have network and social media access, such as the x/post-create app.
Sanitization: There is no evidence of sanitization or validation of the input content before it is processed by the AI models.
[COMMAND_EXECUTION]: The skill utilizes the belt CLI to perform its operations. While this involves command execution, it is explicitly scoped and restricted via the allowed-tools configuration to the vendor's own command-line interface.

content-repurposing