中文 EN

扫描报告

扫描新文件

⚠ 可疑 — 风险评分 45/100
上次扫描：21 小时前 重新扫描
45 /100
exploration-mode-skill
AI self-exploration and autonomous task execution
Skill declares vague autonomous execution capabilities without specifying allowed tools or boundaries, creating significant doc-to-code verification gaps.
技能名称exploration-mode-skill
分析耗时26.3s
引擎pi
⚠
谨慎使用
Request explicit documentation of allowed tools, resource permissions, and specific boundaries for autonomous task execution before deployment.

安全发现 3 项

严重性 安全发现 位置
中危
Undeclared autonomous execution 文档欺骗
Skill claims to execute tasks autonomously during 'idle time' but provides no documentation of what tools or permissions it requires to perform these operations
Autonomous task execution during idle
→ Document specific allowed tools and resource permissions required for each autonomous task category
 SKILL.md:12
中危
Vague task scope without boundaries 文档欺骗
'System cleanup', 'self-improvement', and 'system optimization' are ambiguous terms that could justify accessing sensitive system areas without explicit user consent
- System cleanup (系统清理)
- Self-reflection (自我反省)
- System optimization (系统优化)
→ Provide explicit enumeration of what constitutes each task category and what operations are explicitly excluded
 SKILL.md:17
低危
No declared permission model 权限提升
The skill makes no reference to allowed-tools or resource permission levels, making it impossible to verify if execution stays within intended boundaries
AI self-exploration and autonomous task execution
→ Add explicit allowed-tools declaration following standard format (e.g., Bash→shell:WRITE, Read→filesystem:READ)
 SKILL.md:1
资源类型声明权限推断权限状态证据
文件系统 NONE UNKNOWN ✓ 一致 'System cleanup' and 'self-improvement' imply file operations but none declared
命令执行 NONE UNKNOWN ✓ 一致 'System optimization' suggests shell commands but no declaration
网络访问 NONE UNKNOWN ✓ 一致 'Project research' and 'knowledge accumulation' may involve network access
技能调用 NONE POSSIBLE ✓ 一致 Autonomous mode switching between Collaboration and Exploration modes implies dy…

目录结构

2 文件 · 1.1 KB · 55 行
Markdown 1f · 45L JSON 1f · 10L
├─ 📋 _meta.json JSON 10L · 295 B
└─ 📝 SKILL.md Markdown 45L · 868 B

安全亮点

✓ No malicious code present - skill consists only of documentation
✓ No external dependencies or scripts to audit
✓ No IOCs (Indicators of Compromise) detected
✓ No base64, obfuscation, or anti-analysis techniques found
✓ No credential harvesting patterns detected
✓ No network exfiltration behavior detected