design-system
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, creating an indirect prompt injection attack surface.
- Ingestion points: Processes raw HTML source code, CSS, and page text from live URLs or local files (
SKILL.md). - Boundary markers: No explicit boundary markers or delimiters are defined to instruct the agent to ignore embedded instructions inside the analyzed HTML content.
- Capability inventory: The skill utilizes
Bash,Read,Write, andEdittools, allowing file modifications and command execution (playwright-cli). - Sanitization: No input sanitization or filtering is specified for the extracted web text before processing.
Audit Metadata