可信 — 风险评分 5/100
上次扫描:1 天前 重新扫描
5 /100
proof-agent
Adversarial verification for AI-generated work using GitHub Copilot
A well-documented adversarial verification tool for AI-generated code with no malicious behavior detected.
技能名称proof-agent
分析耗时36.6s
引擎pi
可以安装
This skill is safe to use. No action required.
资源类型声明权限推断权限状态证据
命令执行 WRITE WRITE ✓ 一致 entrypoint.sh:1 — all shell execution is documented in SKILL.md
网络访问 READ READ ✓ 一致 fact-check.sh:48,55,65 — HTTP checks to npm registry, GitHub, and target URLs; d…
文件系统 READ READ ✓ 一致 verify.sh:1 — reads git diffs only; entrypoint.sh:5 — reads verification_prompt.…
环境变量 NONE READ ✓ 一致 action.yml — reads standard GitHub Actions env vars (GITHUB_TOKEN, PR_NUMBER); n…
技能调用 WRITE WRITE ✓ 一致 SKILL.md:1 — explicitly spawns independent verifier subagent via gh copilot
剪贴板 NONE NONE No clipboard access found
浏览器 NONE NONE No browser automation found
数据库 NONE NONE No database access found
1 项发现
🔗
中危 外部 URL 外部 URL
https://x.com/acolombiadev
CONTRIBUTING.md:146

目录结构

11 文件 · 37.4 KB · 1381 行
Markdown 3f · 572L Shell 3f · 448L Python 3f · 280L YAML 1f · 66L TOML 1f · 15L
├─ 📁 proof_agent
│ ├─ 🐍 __init__.py Python 10L · 310 B
│ ├─ 🐍 config.py Python 93L · 2.9 KB
│ └─ 🐍 verifier.py Python 177L · 5.0 KB
├─ 📁 scripts
│ ├─ 🔧 fact-check.sh Shell 136L · 4.0 KB
│ └─ 🔧 verify.sh Shell 88L · 2.5 KB
├─ 📋 action.yml YAML 66L · 2.2 KB
├─ 📝 CONTRIBUTING.md Markdown 152L · 3.2 KB
├─ 🔧 entrypoint.sh Shell 224L · 6.3 KB
├─ 📄 pyproject.toml TOML 15L · 384 B
├─ 📝 README.md Markdown 286L · 6.7 KB
└─ 📝 SKILL.md Markdown 134L · 4.1 KB

依赖分析 1 项

包名版本来源已知漏洞备注
pyyaml >=6.0 pip Version constrained, low-risk dependency

安全亮点

✓ SKILL.md thoroughly documents all capabilities including network calls, shell execution, and subagent invocation
✓ All network requests target legitimate services: GitHub API, npm registry, and explicitly-requested URLs for fact-checking
✓ Python code is clean, readable, and uses standard library + pyyaml (pinned to >=6.0)
✓ No obfuscation, base64 encoding, or anti-analysis techniques found
✓ No credential harvesting or environment variable iteration for secrets
✓ No remote code execution from untrusted sources — curl calls are for verification only
✓ GitHub Actions token access is scoped to GitHub API operations (PR comments) as declared
✓ fact-check.sh is a pure verification utility with no side effects or data exfiltration
✓ Dependencies are minimal (pyyaml) and documented
✓ The skill follows a legitimate adversarial verification pattern (worker vs. verifier separation)