terraform-provider-docs

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and read public Terraform Registry pages (e.g., via web_fetch or curl to URLs on registry.terraform.io, with URL generation shown in scripts/tf_doc_url.py and references/provider-urls.md), so it ingests external, third-party documentation that can directly influence code-generation and tool actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching Terraform Registry documentation at runtime (e.g., https://registry.terraform.io/providers/aliyun/alicloud/latest/docs/resources/forward_entry) via web_fetch/curl and then uses the fetched content to drive the agent's instructions and Terraform code generation, so the external URL is a runtime dependency that directly controls agent behavior.