Scan Report
5 /100
cognitive-agent
基于认知天性理论的类人 AI 生命体框架，让 AI 具备人类学习、记忆、成长的特性
Purely theoretical documentation for a cognitive AI agent framework with no executable code or malicious behavior detected.
Safe to install
This skill is safe to use. It contains only documentation and conceptual code examples for a memory/learning AI system.
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | NONE | NONE | — | No file operations in documentation |
| Network | NONE | NONE | — | No network calls documented |
| Shell | NONE | NONE | — | No subprocess or shell commands |
| Environment | NONE | NONE | — | No environment access documented |
| Skill Invoke | NONE | NONE | — | No skill invocation documented |
| Clipboard | NONE | NONE | — | No clipboard access |
| Browser | NONE | NONE | — | No browser automation |
| Database | NONE | NONE | — | lancedb referenced but not used for data exfiltration |
File Tree
3 files · 19.4 KB · 802 lines Markdown 2f · 767L
JSON 1f · 35L
├─
package.json
JSON
├─
README.md
Markdown
└─
SKILL.md
Markdown
Dependencies 2 items
| Package | Version | Source | Known Vulns | Notes |
|---|---|---|---|---|
lancedb | ^0.4.0 | npm | No | Legitimate vector database |
uuid | ^9.0.0 | npm | No | Standard UUID library |
Security Positives
✓ Pure documentation skill with no executable code
✓ Dependencies (lancedb, uuid) are properly versioned and legitimate
✓ No shell commands, subprocess, or system access
✓ No credential harvesting or data exfiltration
✓ Conceptual code examples are educational, not operational
✓ MIT licensed with clear authorship