polylane

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

• Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to read GitHub pull requests and issues, which can contain outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency exists because the skill instructs the agent to fetch and follow onboarding instructions from a remote URL (https://api.polylane.com/v1/public/setup/prompt.md), constituting an external runtime dependency on unverified remote content.