alibabacloud-emr-spark-manage

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow explicitly instructs the agent to fetch and read job logs and SQL result files from OSS paths (e.g., ListLogContents and ListSqlStatementContents shown in job-management.md and api-reference.md, using fileName like oss://... or HTTPS log URLs returned by GetJobRun), which are user-generated/untrusted third-party content the agent is expected to interpret and that can materially influence actions like canceling jobs or changing configurations.