The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard development tools such as vale, git, and jq. These commands are used as intended for linting prose, managing branches, and processing JSON data.
[DATA_EXPOSURE]: The skill writes temporary linting results to /tmp/vale.json. This is a standard practice for processing tool output and does not involve sensitive user credentials or private data.
[INDIRECT_PROMPT_INJECTION]: The skill processes external documentation files which could theoretically contain malicious instructions. However, the skill implements strict boundary markers by focusing only on specific Vale-defined errors and requires verification through a second linter pass, which mitigates the risk of the agent following instructions found within the text being linted.

fix