qa-only

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

• Third-party content exposure detected (low risk: 0.10). The skill navigates arbitrary web applications and consumes rendered page text and console output, which can contain outsider-authored content.

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

• Potentially malicious external URL detected (high risk: 0.70). The script fetches a shell installer from https://bun.sh/install using curl and executes it to install Bun at runtime when missing, representing a weak/unknown third-party operational dependency.