The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill metadata and quick-start guide instruct the user to install a Go binary from a third-party repository: github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest. This repository is not associated with a known trusted organization or vendor.
[COMMAND_EXECUTION]: The skill functions by executing shell commands via the blogwatcher CLI tool. This includes commands like blogwatcher scan which initiate network connections to external, user-specified URLs.
[PROMPT_INJECTION]: The skill provides an interface for the agent to ingest and process untrusted data from RSS and Atom feeds, creating an indirect prompt injection surface.
Ingestion points: External content is fetched through the scan and articles commands.
Boundary markers: Absent; there are no delimiters or instructions provided to the agent to treat the retrieved feed data as untrusted.
Capability inventory: The agent can execute CLI commands and manage a local database of articles.
Sanitization: The instructions do not include any steps for sanitizing or validating the content retrieved from external feeds before the agent interprets it.

blogwatcher