The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the blogwatcher CLI tool from a third-party GitHub repository (github.com/Hyaxia/blogwatcher) that does not belong to a verified or trusted organization.
[REMOTE_CODE_EXECUTION]: The installation command go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest fetches, compiles, and installs code from a remote source, allowing the execution of third-party logic on the user's system.
[COMMAND_EXECUTION]: The skill uses the blogwatcher binary to perform various operations such as scanning blogs and reading articles, which involves executing code on the local system.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external RSS/Atom feeds.
Ingestion points: External blog feeds are ingested via blogwatcher scan and blogwatcher articles.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill definition.
Capability inventory: The agent can execute shell commands via the blogwatcher tool and potentially other system tools depending on the environment.
Sanitization: No sanitization or filtering of feed content is implemented before the data is presented to the agent.

blogwatcher