antigravity-skills-manager

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

• Third-party content exposure detected (low risk: 0.10). The skill installs agent skills from a public GitHub repository catalog where an attacker could publish malicious content in skill definitions.

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 agent skills from an arbitrary open-source GitHub repository and npm package (rmyndharis/antigravity-skills) whose content governs future agent sessions, presenting an unverifiable unofficial operational dependency.