role-creator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run "find-skills", resolve and install remote scoped skills (e.g., antfu/skills@vitest) and to invoke installed skills at runtime, meaning it will fetch and execute untrusted third-party skill packages that can change agent behavior.