canary

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

• Third-party content exposure detected (low risk: 0.10). The canary skill navigates to arbitrary user-supplied URLs and captures text/screenshots from live web pages.

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency on bun's installer script (https://bun.sh/install) is fetched and executed via curl and bash if the bun command is missing during setup, presenting a weak/unknown provenance tier due to lack of strict integrity enforcement beyond raw checksum verification.