The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the blogwatcher CLI tool via a Go module from an unverified GitHub repository (github.com/Hyaxia/blogwatcher).- [COMMAND_EXECUTION]: The skill executes the blogwatcher binary to perform tasks like adding blogs, listing articles, and scanning for updates.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of external RSS/Atom feed content.
Ingestion points: Untrusted data enters the agent context through the blogwatcher scan and blogwatcher articles commands as defined in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external feed content as untrusted data.
Capability inventory: The agent is configured to execute the blogwatcher CLI and process its outputs, which contains the external data.
Sanitization: There is no evidence of filtering or sanitization of the feed content before it is presented to the agent.

blogwatcher