tab-accordion

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

• Third-party content exposure detected (medium risk: 0.30). The workflow directs the agent to a GitHub repository and reference file, which involves reading external repository content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch and install external operational content from the unofficial GitHub repository kostja94/bricks via an npx command, introducing a common unofficial operational dependency.