扫描报告
0 /100
oatda-text-completion
Generate text using OATDA's unified LLM API with support for 10+ providers
This is a pure documentation skill for text completion via the OATDA unified API. All behavior is clearly declared and documented; no hidden functionality or malicious patterns detected.
可以安装
No action required. This skill is a straightforward LLM API wrapper with transparent documentation.
| 资源类型 | 声明权限 | 推断权限 | 状态 | 证据 |
|---|---|---|---|---|
| 网络访问 | READ | READ | ✓ 一致 | curl POST to https://oatda.com/api/v1/llm (line 57-63) |
| 命令执行 | WRITE | WRITE | ✓ 一致 | Executes curl and jq commands (line 19, 57) |
| 文件系统 | READ | READ | ✓ 一致 | Reads ~/.oatda/credentials.json (line 19) |
| 环境变量 | READ | READ | ✓ 一致 | Accesses OATDA_API_KEY env var (line 19) |
4 项发现
中危 外部 URL 外部 URL
https://oatda.com SKILL.md:4 中危 外部 URL 外部 URL
https://oatda.com/api/v1/llm SKILL.md:57 中危 外部 URL 外部 URL
https://oatda.com/dashboard/api-keys SKILL.md:98 中危 外部 URL 外部 URL
https://oatda.com/dashboard/usage SKILL.md:99 目录结构
1 文件 · 4.2 KB · 127 行 Markdown 1f · 127L
└─
SKILL.md
Markdown
安全亮点
✓ Full documentation of all API calls and parameters
✓ API key security practice: only shows first 8 characters
✓ Clear error handling for HTTP status codes (401, 402, 429, 400)
✓ Dependencies (curl, jq) and config paths declared upfront
✓ Legitimate use case: unified LLM API wrapper
✓ No base64 encoding, eval(), or suspicious patterns
✓ No hidden instructions in comments
✓ No credential exfiltration beyond necessary API usage