glm-master-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's "How an Agent should use this Master Skill" instructs the agent to open and follow external skills' SKILL.md files (links to public GitHub repos such as https://github.com/zai-org/GLM-skills and other public docs URLs), which are untrusted, user-controlled third-party content that the agent would read and act on.