The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions and a JSON evaluation file. There are no executable scripts (.sh, .py, .js) or binaries included in the package.
[DATA_EXPOSURE]: The skill instructs the agent to read context from .agents/product-marketing-context.md if it exists. This is a standard practice for retrieving brand-specific guidelines and does not involve accessing sensitive system credentials or private user files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied text for editing. While this input is untrusted, the skill possesses no high-risk capabilities (such as network access, file writing, or command execution) that could be leveraged by a malicious prompt embedded in the copy.
[COMMAND_EXECUTION]: No shell commands or subprocess calls were detected in any of the analyzed files.

copy-editing