The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions and metadata specify the installation of the blogwatcher binary from a public GitHub repository (github.com/Hyaxia/blogwatcher) using go install.- [COMMAND_EXECUTION]: The skill uses the blogwatcher command-line tool to perform operations such as adding blogs, scanning for updates, and marking articles as read.- [SAFE]: The skill processes content from external RSS and Atom feeds, which presents a surface for indirect prompt injection. However, this is inherent to the skill's purpose of monitoring web feeds.
Ingestion points: External feed content retrieved via blogwatcher scan and blogwatcher articles commands.
Boundary markers: The skill does not explicitly define markers to encapsulate untrusted feed data within the agent's context.
Capability inventory: The skill's capabilities are limited to executing the blogwatcher CLI tool for feed management.
Sanitization: Content sanitization is managed by the external blogwatcher utility.

blogwatcher