The Agent Skills Directory

[SAFE]: The skill's functionality is limited to text analysis and scoring based on provided story outlines. No suspicious commands, network requests, or data exfiltration patterns were detected in the instructions or reference files.
[SAFE]: The skill uses natural language constraints to ensure evaluations are based strictly on the provided content, which helps mitigate basic instruction override attempts within the processed text.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (story outlines). While this represents a theoretical attack surface, the risk is negligible as the skill lacks any tools or capabilities (no file writes, no network operations, no command execution) to perform harmful actions beyond generating text.

story-outline-evaluator