The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions for text editing and copywriting. It does not contain any executable scripts, remote dependencies, or hidden logic.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-supplied text. While this creates a surface for indirect prompt injection where malicious instructions could be embedded in the input text, the skill does not use high-risk tools (such as network access or shell execution) that would allow such an injection to be exploited for data exfiltration or system compromise. The risk is limited to the agent potentially following stylistic instructions embedded in untrusted data.
[COMMAND_EXECUTION]: The skill lists file manipulation tools (Read, Write, Edit, Glob, Grep) in its configuration, which are appropriate and necessary for its stated purpose of editing prose files within a project. No malicious or unnecessary command patterns were identified in the instructions.

antislop-copywriting