eliza-cloud-manage-domain

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to perform live status checks using "direct HTTP/DNS/RDAP requests" against user domains (SKILL.md) and to re-check user-published TXT verification records for external domains (references/api-shape.md), which ingest arbitrary, public/untrusted third-party content as part of its workflow.