versus

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

• Third-party content exposure detected (high risk: 0.90). The skill performs WebFetch calls to the external API https://vibeindex.ai/api/resources?ref=skill-versus&search={...} and ingests resource fields (description, tags, etc.) returned from that public site—user-supplied/untrusted content—which the agent reads and uses in its comparison workflow, enabling possible indirect prompt injection.