The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions are purely focused on stylistic editing and do not contain any commands designed to bypass safety filters or override the agent's core instructions.
[EXTERNAL_DOWNLOADS]: The skill includes a reference link to a well-known and trusted service (Wikipedia) for documentation purposes. It does not download or execute any external code.
[DATA_EXFILTRATION]: There are no indicators of data collection, hardcoded credentials, or unauthorized network operations. The tools requested (Read, Write, Edit) are consistent with the skill's purpose as a text editor.
[REMOTE_CODE_EXECUTION]: The skill does not perform any package installations or remote script executions.
[COMMAND_EXECUTION]: No shell commands or subprocess spawning patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for editing, which is an inherent attack surface for indirect prompt injection. However, the instructions are highly specific to linguistic transformation, and there is no evidence of unsafe interpolation or execution of the input content.

humanizer