The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill is configured to install the blogwatcher utility from a third-party GitHub repository (github.com/Hyaxia/blogwatcher) that does not belong to the skill author or a known trusted organization.
[COMMAND_EXECUTION]: The skill relies on executing the blogwatcher binary to perform its tasks, including managing local data and making network requests to fetch feed updates.
[PROMPT_INJECTION]: The skill monitors external RSS and Atom feeds, which are sources of untrusted data. If an agent processes or summarizes content from these feeds, it could be susceptible to indirect prompt injection attacks designed to manipulate the agent's behavior.
Ingestion points: Content from RSS/Atom feeds retrieved via blogwatcher scan and blogwatcher articles.
Boundary markers: None present in the instructions to delimit external content or warn the agent about potentially malicious instructions within the feeds.
Capability inventory: The agent has access to the blogwatcher CLI tool and potentially other shell capabilities depending on the environment.
Sanitization: No sanitization or validation of the feed content is performed before it is presented to the agent.

blogwatcher