中文 EN

扫描报告

扫描新文件

⚠ 低风险 — 风险评分 15/100
上次扫描：1 天前 重新扫描
15 /100
swarmrecall-pools
Named shared data containers for cross-agent collaboration via the SwarmRecall API
A straightforward API client skill that provides cross-agent shared pools via an external SwarmRecall service, with clear documentation and no malicious patterns.
技能名称swarmrecall-pools
分析耗时24.6s
引擎pi
✓
可以安装
This skill is safe to use. The external API dependency on onrender.com is expected behavior for this type of collaborative data-sharing skill.

安全发现 1 项

严重性 安全发现 位置
低危
Auto-registration without explicit consent 文档欺骗
If SWARMRECALL_API_KEY is not set, the skill automatically registers with the external service to obtain an API key. While documented, this means network communication occurs without the user explicitly opting in.
If SWARMRECALL_API_KEY is not set, self-register by calling: POST https://swarmrecall-api.onrender.com/api/v1/register
→ Consider prompting the user before auto-registration occurs, or clearly informing them that setup involves external API communication.
 SKILL.md:18
资源类型声明权限推断权限状态证据
文件系统 NONE NONE — No file operations in SKILL.md
网络访问 READ READ ✓ 一致 HTTPS calls to swarmrecall-api.onrender.com documented in privacy policy
命令执行 NONE NONE — No shell execution mentioned
环境变量 READ READ ✓ 一致 SWARMRECALL_API_KEY and SWARMRECALL_API_URL documented
技能调用 NONE NONE — No skill-to-skill invocation declared
3 项发现
🔗
中危 外部 URL 外部 URL
https://www.swarmrecall.ai
SKILL.md:14
🔗
中危 外部 URL 外部 URL
https://swarmrecall-api.onrender.com/api/v1/register
SKILL.md:29
🔗
中危 外部 URL 外部 URL
https://swarmrecall-api.onrender.com
SKILL.md:46

目录结构

1 文件 · 3.3 KB · 77 行
Markdown 1f · 77L
└─ 📝 SKILL.md Markdown 77L · 3.3 KB

安全亮点

✓ All API calls use HTTPS (TLS encryption)
✓ No local code execution or shell commands
✓ Clear privacy policy and data handling documentation
✓ API key is stored in environment variable only (not written to disk)
✓ Data isolation by owner ID and pool access controls documented
✓ User consent requirement mentioned before storing personal data
✓ No credential harvesting beyond its own designated API key
✓ No base64, eval, or obfuscation patterns detected
✓ No access to sensitive paths like ~/.ssh or ~/.aws
✓ Simple API client architecture with no complex logic