dependency-analyzer

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md's required workflow and examples explicitly run tools like "npm audit", "npm outdated", and "pip-audit" (see "分析流程", "使用示例", and "常用命令"), which fetch vulnerability data and package metadata from public package registries and advisory databases (user-uploaded/untrusted content) that the agent parses and uses to make update/mitigation decisions, so external content could influence behavior.