jq-json-processing

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows fetching and piping data from public/untrusted endpoints (e.g., "curl -s https://api.example.com/data | jq '.results'" and "cat urls.txt | xargs -I {} curl -s {} | jq '.data'"), meaning the agent would read and act on arbitrary third‑party JSON that could influence downstream processing or decisions.