alibabacloud-terraform-code-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory Step 4.2 "WebFetch" fetches provider docs from public GitHub raw URLs (https://raw.githubusercontent.com/.../website/docs/{r|d}/<doc_name>.html.markdown) and Step 4.3 requires reciting and using those fetched docs to drive HCL generation, so external, public third‑party content is read and directly influences the agent's actions and outputs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly WebFetches provider docs at runtime (e.g. https://raw.githubusercontent.com/aliyun/terraform-provider-alicloud/master/website/docs/{r|d}/<doc_name>.html.markdown), and that fetched content is required and injected into the model's recitation/generation steps, so remote content directly controls agent instructions.