The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill is purely instructional and defines how to format text and JSON output based on user inputs.
[SAFE]: No remote code execution or external downloads were identified. The skill does not reference any external URLs or scripts.
[SAFE]: No sensitive data exposure or privilege escalation risks are present.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes user-provided JSON input to generate component specifications and drawing plans. This creates a surface where malicious input could influence the generated output. However, the risk is minimal as the skill does not possess capabilities to execute code or access sensitive data. \n
Ingestion points: User-provided JSON data (Input Model) in SKILL.md. \n
Boundary markers: JSON code blocks. \n
Capability inventory: No high-privilege capabilities or dangerous tools detected. \n
Sanitization: No explicit sanitization or filtering instructions provided.

tui-mask