citedy-warm-lead

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow calls Citedy’s warm-lead endpoints, which (per the described “evidence URLs/snippets” and “recent account signals”) necessarily ingest and return third-party web/account text as evidence into the agent’s LLM context, creating an indirect prompt-injection surface from outsider-authored content.