扫描报告
0 /100
agent-budget-controller
Control LLM API spending per agent with daily/weekly/monthly budget limits and alerts
This is a legitimate LLM budget tracking utility with zero external dependencies, no network access, and clean filesystem operations. All capabilities are accurately declared and the code performs exactly as documented.
可以安装
No action needed. This skill is safe for distribution.
| 资源类型 | 声明权限 | 推断权限 | 状态 | 证据 |
|---|---|---|---|---|
| 文件系统 | WRITE | WRITE | ✓ 一致 | lib/config.py:39-42 writes config.json; lib/tracker.py:35-43 appends to usage.js… |
| 网络访问 | NONE | NONE | — | No urllib, requests, socket imports or network calls in entire codebase |
| 命令执行 | NONE | NONE | — | No subprocess, os.system, or shell execution in scripts/budget.py |
| 环境变量 | NONE | NONE | — | No os.environ access in any module |
| 技能调用 | NONE | NONE | — | No skill invocation or inter-process communication |
| 剪贴板 | NONE | NONE | — | No clipboard access detected |
| 浏览器 | NONE | NONE | — | No browser or web automation detected |
| 数据库 | NONE | NONE | — | Uses JSON file storage only, no database connections |
2 项发现
提示 邮箱 邮箱地址
[email protected] EXAMPLE.md:447 提示 邮箱 邮箱地址
[email protected] pyproject.toml:9 目录结构
16 文件 · 77.1 KB · 2768 行 Markdown 6f · 1712L
Python 9f · 1033L
TOML 1f · 23L
├─
▾
lib
│ ├─
__init__.py
Python
│ ├─
alerts.py
Python
│ ├─
config.py
Python
│ ├─
pricing.py
Python
│ ├─
reporter.py
Python
│ └─
tracker.py
Python
├─
▾
scripts
│ └─
budget.py
Python
├─
▾
tests
│ ├─
__init__.py
Python
│ └─
test_budget.py
Python
├─
COMPLETION_REPORT.md
Markdown
├─
EXAMPLE.md
Markdown
├─
INSTALL.md
Markdown
├─
pyproject.toml
TOML
├─
README.md
Markdown
├─
SKILL.md
Markdown
└─
SUMMARY.md
Markdown
依赖分析 1 项
| 包名 | 版本 | 来源 | 已知漏洞 | 备注 |
|---|---|---|---|---|
stdlib-only | N/A | python | 否 | No external dependencies - uses only json, pathlib, datetime, collections, argparse, sys |
安全亮点
✓ Zero external dependencies - pure Python stdlib only
✓ No network access - all data stored locally in ~/.openclaw/budget/
✓ No shell execution or command injection vectors
✓ No credential harvesting or sensitive path access
✓ Clean, readable code without obfuscation
✓ SKILL.md accurately describes all functionality
✓ pyproject.toml correctly declares no dependencies
✓ Uses standard JSON file operations for local persistence