brand-guidelines

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

• Third-party content exposure detected (low risk: 0.10). The agent extracts brand guidelines from user-selected website URLs or artifacts provided during execution.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the execution of npx --yes notugly ... commands during runtime, which introduces an unverifiable third-party package dependency from an unknown publisher.