The Agent Skills Directory

[SAFE]: The skill instructions and associated files are purely technical, focusing on the generation of SVG illustrations through geometric computation and CSS styling. No malicious patterns or security risks were detected.
[PROMPT_INJECTION]: The instructions in SKILL.md are descriptive and technical. There are no attempts to override system prompts, bypass safety filters, or use jailbreak-style language.
[DATA_EXFILTRATION]: No sensitive file paths, credential markers, or unauthorized network operations were identified. The skill does not access environment variables or private user data.
[EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads. All referenced assets, including assets/iso.ts, assets/diagram.css, and assets/figure-scaffold.tsx, are local files provided within the skill package.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download and execution of remote scripts. The verification steps in references/verification.md suggest using browser automation tools to inspect the generated output, which is a standard development practice for UI verification and does not involve untrusted remote code.
[DYNAMIC_EXECUTION]: The skill uses local TypeScript functions in assets/iso.ts to compute geometry and React components in assets/figure-scaffold.tsx to structure SVG markup. It does not use eval() or exec() on untrusted input.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests user input for diagram labels and titles, the use of structured JSX components for SVG generation provides inherent mitigation against common injection attacks in the output. The instructions focus on technical precision rather than processing complex natural language instructions from third parties.

draw-technical-diagrams