Service Creator

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and templates explicitly fetch and parse data from external public APIs (e.g., https://api.example.com/stock/... in reference/templates-stock-monitor.md and similar https/urllib requests in templates and SKILL.md Step 2), require that fetched untrusted data be inspected during dry-run (reference/dry-run.md) and then used to decide whether to call the LLM/invoke API, so arbitrary third-party content can materially influence decisions and tool use.