The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses clear instructional language to guide the AI's behavior as a writing coach. No attempts to bypass safety filters or override system constraints were detected.
[DATA_EXFILTRATION]: There are no network operations (e.g., curl, wget) or attempts to access sensitive system files. The skill operates entirely within the context of writing assistance.
[REMOTE_CODE_EXECUTION]: No remote scripts or external packages are downloaded or executed. The skill relies solely on provided instructions and internal markdown references.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for coaching and revision purposes. While this constitutes an ingestion point for untrusted data, the skill lacks dangerous capabilities (like file writing or network access) that could be exploited through injection. The risk is considered minimal and inherent to the skill's primary function.
[COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the instructions.

coach