exporting-to-png
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using
npx,node -e,docker, and various CLI utilities likesilicon,inkscape, andconvertto perform file conversions. - [EXTERNAL_DOWNLOADS]: The skill uses
npxanddockerto fetch official packages and container images from well-known registries like NPM and Docker Hub. - [PROMPT_INJECTION]: The skill renders untrusted HTML, SVG, and Mermaid content, creating a surface for indirect prompt injection. 1. Ingestion points: Content is passed to rendering engines in
SKILL.md. 2. Boundary markers: No delimiters are specified to isolate user content. 3. Capability inventory: The skill has access to subprocess execution and potentially the local filesystem via browser engines inSKILL.md. 4. Sanitization: No sanitization or escaping of user input is performed before rendering.
Audit Metadata