illustration-grainy-gouache
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/render.mjsexecutes the static shell commandnpm root -gto locate global Node.js packages. This is a standard environment-discovery operation and does not involve user-supplied input. - [EXTERNAL_DOWNLOADS]: The skill requires the standard, well-known Node.js packages
playwrightorplaywright-coreto render SVG files into PNG format. These are established industry-standard tools. - [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts to generate SVG code, creating a potential attack surface for indirect prompt injection. However, this is mitigated by the
scripts/lint.mjstool, which enforces strict security rules by checking for and blocking dangerous SVG features such as<script>tags,<foreignObject>elements, and external URL references. - [SAFE]: No malicious patterns or data exfiltration attempts were identified. The skill follows secure design principles by providing tools for both generating and validating content within a restricted environment.
Audit Metadata