The Agent Skills Directory

[SAFE]: The skill is designed to create self-contained interactive HTML artifacts for educational purposes, which is a benign and productive use case.
[EXTERNAL_DOWNLOADS]: The skill references standard and trusted third-party libraries for visualization (such as D3.js, Chart.js, and Plotly) via official CDN links, which are considered safe sources.
[REMOTE_CODE_EXECUTION]: Instructions in the pattern catalog provide security guidance, specifically advising the author to avoid using eval() and to ensure that interactive inputs are handled safely.
[SAFE]: No evidence of prompt injection, data exfiltration, or malicious persistence mechanisms was found in the instructions or metadata files.
[SAFE]: The skill's ingestion of external data for research is handled safely, as the agent's role is restricted to summarizing and visualizing information rather than executing it.
Ingestion points: Research from primary or official sources as defined in the SKILL.md workflow.
Boundary markers: Not explicitly required as the researched data is used for content generation rather than logic control.
Capability inventory: The skill is limited to creating .html files with inline scripts; it contains no instructions for subprocess execution, network exfiltration, or privileged system access.
Sanitization: The reference documents advise on using safe input handling for interactive models.

visual-learner