skills-cli

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

• Third-party content exposure detected (high risk: 0.90). This skill's Discovery Workflow explicitly directs the agent to check public sites like https://skills.sh and to inspect source repositories (GitHub, GitLab, "any git URL") and install counts/repo stars—all untrusted, user-generated third-party content that the agent is expected to read and use to decide which skills to recommend or install.