The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): The instructions are focused on document structure and writing principles. No override commands or safety bypass patterns were detected.
[DATA_EXFILTRATION] (SAFE): No network operations (curl, wget, fetch) or sensitive file path references exist in the skill.
[REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute remote scripts. The 'npm install' mention in the documentation template is static text for user guidance and not an executable command.
[COMMAND_EXECUTION] (SAFE): No subprocess spawning or shell command execution logic is present.
[INDIRECT_PROMPT_INJECTION] (INFO): While the skill processes user-provided information to generate documents, it has no side-effect capabilities (file writing, network access), making the risk negligible.

document-writer