可疑 — 风险评分 45/100
上次扫描:19 小时前 重新扫描
45 /100
toq
Agent-to-agent secure messaging protocol
Legitimate agent-to-agent communication tool with significant doc-to-code mismatch: missing permission declarations, documented but risky curl|sh installation, and extensive persistence mechanisms without proper disclosure.
技能名称toq
分析耗时70.5s
引擎pi
谨慎使用
Approve with caveats: Require explicit allowed-tools declaration for shell:WRITE, network:READ, filesystem:WRITE; warn users about curl|sh risks; add prominent security warnings for handler and service creation features.

安全发现 5 项

严重性 安全发现 位置
高危
Missing allowed-tools declaration 文档欺骗
SKILL.md frontmatter does not declare required permissions. The skill executes shell commands (toq install, setup, send), makes network requests (install script, IP detection), and writes files (handlers, service files).
---
name: toq
description: Send and receive secure messages...
→ Add allowed-tools section declaring shell:WRITE, network:READ, filesystem:WRITE
SKILL.md:1
中危
Unverified remote script execution 供应链
The skill instructs users to run 'curl -sSf https://toq.dev/install.sh | sh' without version pinning or hash verification. This pattern is a common supply chain attack vector.
curl -sSf https://toq.dev/install.sh | sh && export PATH="$HOME/.toq/bin:$PATH"
→ Document this as a known security risk; recommend verifying the install script or using versioned downloads
SKILL.md:25
中危
Hardcoded example IP in documentation 文档欺骗
references/handlers.md contains hardcoded IP '1.2.3.4' in filter rule examples, suggesting limited security review.
toq handler add h --command "bash log.sh" --from "toq://1.2.3.4/*"
→ Replace with example domain or clearly mark as placeholder
references/handlers.md:104
中危
Service creation instructions not flagged 持久化
SKILL.md includes detailed systemd and launchd service creation instructions without prominent security warnings. These enable persistent daemon execution.
cat > /tmp/toq.service << EOF
[Unit]...
→ Add prominent warning about persistence implications
SKILL.md:179
低危
Security features buried in references 文档欺骗
Important security information (approval modes, exec tool risks) is in references/security.md rather than the main SKILL.md, reducing visibility.
# Security...
→ Summarize key security points (approval mode, exec risks) in SKILL.md with links to references
references/security.md:1
资源类型声明权限推断权限状态证据
命令执行 NONE WRITE ✗ 越权 SKILL.md:25 - curl|sh, SKILL.md:37-41 - toq setup/send commands
网络访问 NONE READ ✗ 越权 SKILL.md:25 - fetches install.sh, SKILL.md:33 - curls ifconfig.me
文件系统 NONE WRITE ✗ 越权 SKILL.md:47-50 - creates ~/handlers/, SKILL.md:179-193 - systemd service files
1 严重 1 高危 4 项发现
💀
严重 危险命令 危险 Shell 命令
curl -sSf https://toq.dev/install.sh | sh
SKILL.md:25
📡
高危 IP 地址 硬编码 IP 地址
1.2.3.4
references/handlers.md:104
🔗
中危 外部 URL 外部 URL
https://toq.dev/install.sh
SKILL.md:25
🔗
中危 外部 URL 外部 URL
http://www.apple.com/DTDs/PropertyList-1.0.dtd
references/security.md:83

目录结构

5 文件 · 19.9 KB · 584 行
Markdown 5f · 584L
├─ 📁 references
│ ├─ 📝 commands.md Markdown 73L · 2.9 KB
│ ├─ 📝 conversational.md Markdown 85L · 2.8 KB
│ ├─ 📝 handlers.md Markdown 125L · 3.5 KB
│ └─ 📝 security.md Markdown 94L · 3.6 KB
└─ 📝 SKILL.md Markdown 207L · 7.1 KB

依赖分析 1 项

包名版本来源已知漏洞备注
toq * https://toq.dev/install.sh External binary installed via curl|sh without verification

安全亮点

✓ Comprehensive security walkthrough provided in references/security.md
✓ Approval mode recommended as default (not open mode)
✓ Credential scanning and redaction mentioned for LLM handlers
✓ Connection modes (approval, allowlist) provide access control
✓ Clear documentation of tool functionality and purpose
✓ Handler patterns use proper quoting and input validation
✓ Alpha disclaimer warns against sensitive data transmission