svelte-ui-animator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and analyze existing project files, including component source code and configuration files, to determine how to implement animations. This creates a vulnerability where malicious instructions hidden in the analyzed codebase could influence the agent's behavior.
- Ingestion points: Project files in
src/routes/,src/lib/components/,tailwind.config.js, andapp.htmlare scanned during Phase 1 as described inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore potentially malicious instructions embedded within the analyzed project files.
- Capability inventory: The agent has the capability to write new components, modify Tailwind configurations, and update global CSS files.
- Sanitization: No validation or sanitization of the ingested code content is performed before it is used to generate implementation plans.
Audit Metadata