The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and prompt templates for LLM evaluation. No executable code or risky operations were found in the provided documentation.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or network operations were identified. The skill does not perform any data exfiltration.
[PROMPT_INJECTION]: While the templates process external data (prompts and responses), the skill is purely instructional and does not provide instructions to bypass agent safety filters or override core behavior. It lacks the capabilities (e.g., shell access, network access) that would make indirect prompt injection a high-risk concern.

advanced-evaluation