The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires downloading the blogwatcher CLI tool from a third-party repository on GitHub (github.com/Hyaxia/blogwatcher).- [REMOTE_CODE_EXECUTION]: The installation command go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest downloads and executes code from a remote source at runtime during the installation process.- [COMMAND_EXECUTION]: The skill's operation relies on the execution of the blogwatcher binary for monitoring feeds and managing articles.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from external RSS and Atom feeds. 1. Ingestion points: Feed content is retrieved and displayed via the scan and articles commands in SKILL.md. 2. Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish between the tool's output and the potentially untrusted content of the feeds. 3. Capability inventory: The skill provides a suite of CLI commands (add, scan, read, etc.) to interact with the feed data. 4. Sanitization: The instructions do not mention any sanitization or filtering of the feed content before it is processed by the agent.

blogwatcher