gitcode

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly accepts user-provided tokens and instructs including them verbatim in request headers or query params (e.g., PRIVATE-TOKEN/Authorization/access_token), which requires the LLM to handle and output secret values directly.

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

• Third-party content exposure detected (medium risk: 0.30). 该 skill 运行时会通过 GitCode API 读取仓库内容（如 GET /repos/{owner}/{repo}/issues/{number}/comments、GET /repos/{owner}/{repo}/pulls/{number}/comments、GET /repos/{owner}/{repo}/raw/{path} 等，具体输入由调用方选择 owner/repo/issue/PR/path），而这些内容可能包含第三方用户在 Issues/PR/文件中的自由文本，从而构成间接提示注入暴露面。