liveblocks-ui-skills
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill incorporates guidelines from an external repository (
github.com/VoltAgent/awesome-design-md) which is not a recognized trusted source. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process external documentation (
DESIGN.md) to define visual tokens. This process lacks clear boundary markers or sanitization, allowing potentially malicious instructions in the external file to influence the agent. - Ingestion points: External
DESIGN.mdfile referenced via GitHub URL. - Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore potential commands in the fetched file.
- Capability inventory: The skill restricts UI layout, typography, and color enforcement.
- Sanitization: Absent; the fetched content is processed by a "drift scanner" without mentioned validation steps.
Audit Metadata