vastai-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries Vast.ai public endpoints (e.g., the "/bundles" offers search called out in SKILL.md and references/api.md) to fetch marketplace offers—third-party/provider-generated content—which the agent must read and use to select/create instances, so untrusted remote content can materially influence actions.