The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any executable scripts, binaries, or suspicious commands. Its primary function is to guide an AI agent through a design process.
[DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials, sensitive file path accesses, or unauthorized network operations were detected. All external links in references/sources.md point to well-known academic, government, and industry resources (e.g., NASA, IBM, W3C, Library of Congress) for documentation and citation purposes.
[PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override agent behavior. The skill includes explicit directives to avoid fabricating data, which aligns with AI safety best practices.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to generate visuals. It proactively mitigates injection risks by instructing the agent to verify sources, avoid inventing statistics, and keep evidence limitations visible in the final output, as detailed in references/evidence.md and SKILL.md.
[EXTERNAL_DOWNLOADS]: No remote code execution or package installation patterns were identified. The external URLs provided are for reading material and do not involve runtime script execution.

infographic