deploy-skills-in-antigravity

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

• Third-party content exposure detected (low risk: 0.10). The skill installs external repositories and agent skills via npx skills add from arbitrary GitHub URLs provided by the user, but it does not automatically consume unselected outsider feeds without user request.

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 download and install third-party packages or repository contents via npx skills add from arbitrary user-provided or referenced GitHub URLs, constituting an unverifiable runtime external dependency under the dependency gate.