data-quality

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md companion check explicitly instructs the agent to run shell commands that may fetch and install remote packages (e.g., "npx skills add ...") and the references include commands to clone public repos (references/lineage-tools.md: "git clone https://github.com/MarquezProject/marquez.git"), meaning the agent is directed to fetch and potentially load untrusted third-party content that could influence subsequent behavior.