The Agent Skills Directory

[SAFE]: No executable scripts or code files are included in this skill. It operates entirely within the LLM's prompt context.
[SAFE]: No external dependencies, package managers (npm/pip), or remote code execution patterns were detected.
[SAFE]: No network operations or data exfiltration vectors are present.
[SAFE]: No hardcoded credentials or sensitive file path access were identified.
[PROMPT_INJECTION]: The instructions follow standard formatting and do not attempt to bypass safety filters or override the agent's core behavioral constraints.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input (prompts to be reviewed). While this creates a potential surface for indirect injection, the skill's logic is focused on analysis and rewriting, which is inherently safe for this specific use case. No specific vulnerabilities were found in the processing logic.

prompt-reviewer