skills-cli

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to discover and install skills from public, user-generated sources (e.g., checking skills.sh and using "bunx skills find" / "bunx skills add" with GitHub, GitLab, or any git URL), meaning the agent will read and act on untrusted third-party content that can influence tool usage and next actions.