nby-awesome-design-md

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The workflow clones a public GitHub repository at runtime and then copies/reads design-md/$BRAND/DESIGN.md from that repo into the project root, so outsider-authored free text from the public web (VoltAgent/awesome-design-md) is ingested into the agent’s LLM context via the applied DESIGN.md content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill clones/pulls https://github.com/VoltAgent/awesome-design-md.git at runtime and then reads DESIGN.md files from that repo which it explicitly requires as the single source of truth to control generation instructions and UI prompts.