library

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

• Third-party content exposure detected (high risk: 0.90). The skill's create and playbook creation flows explicitly accept external "sources" as URLs (see "Interactive Flow for Playbooks" and the create_entity/create_playbook examples) and includes resource tools (create_resource, search_resources) that ingest URL/third-party content which the agent is expected to read and use to generate/update entities, allowing untrusted web content to influence agent actions.