alibabacloud-oss-media-process

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts arbitrary HTTP(S) URLs via the --uri flow (see SKILL.md "Choose the source" / --uri description) and runs media/IMM operations (e.g., codes, blindwatermark-extract, label/score/detection) whose text/metadata outputs the agent must read and use to decide follow-up actions, so it clearly ingests untrusted third-party content that could carry indirect prompt-injection payloads.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite explicitly runs a remote install script via curl -fsSL https://aliyuncli.alicdn.com/setup.sh | bash at runtime, which fetches and executes remote code and is presented as a required installation step, so it directly executes external code.