alibabacloud-find-skills

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls the public AgentExplorer APIs (e.g., aliyun agentexplorer get-skill-content) to fetch public/community-contributed skill markdown (see Core Workflow / Step 3 and references/ram-policies.md listing GetSkillContent), and that fetched, untrusted content is used to verify and decide whether to install/run skills—allowing third-party content to influence agent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's installation instructions instruct running a runtime fetch-and-execute command (curl -fsSL https://aliyuncli.alicdn.com/setup.sh | bash), which downloads and executes remote code as a required setup step, so this URL poses an execution/control risk.