The Agent Skills Directory

SAFE (SAFE): No security issues were detected across any of the 10 threat categories. The skill is composed exclusively of Markdown files providing structural templates for educational tasks.- NO_CODE (SAFE): The skill does not include any scripts (Python, JavaScript, shell), binaries, or configuration files that could trigger execution.- Indirect Prompt Injection (SAFE): The skill has an ingestion surface for untrusted user data (e.g., explaining user-provided topics), but it possesses no dangerous capabilities such as file system access, network requests, or command execution. Analysis of the evidence chain: (1) Ingestion points: User-provided topics/text via SKILL.md triggers; (2) Boundary markers: Absent; (3) Capability inventory: Text generation only; (4) Sanitization: Absent. The lack of dangerous capabilities renders this surface safe.

learning-education