Scan Report
20 /100
agent-guardian
AI助手体验守护系统:看门狗监控、智能状态汇报、即时查询、语言一致性过滤、消息队列追踪
A legitimate AI assistant monitoring/guardian skill with appropriate file and shell permissions for status tracking and language filtering. No malicious behavior detected.
Safe to install
Approve for use. Consider pinning langdetect version in install.sh for better supply chain hygiene.
Findings 2 items
| Severity | Finding | Location |
|---|---|---|
| Low | Unpinned dependency version Supply Chain | scripts/install.sh:53 |
| Low | Systemd service runs as root Priv Escalation | scripts/install.sh:73 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | WRITE | WRITE | ✓ Aligned | install.sh:52 writes to /tmp, patch scripts modify plugin dirs |
| Shell | WRITE | WRITE | ✓ Aligned | supervisor.sh, install.sh use subprocess calls |
| Environment | NONE | READ | ✓ Aligned | Scripts read PATH, HOME but no sensitive keys |
| Network | NONE | NONE | — | Uses openclaw CLI only, no raw network calls |
| Skill Invoke | NONE | NONE | — | N/A |
| Clipboard | NONE | NONE | — | N/A |
| Browser | NONE | NONE | — | N/A |
| Database | NONE | NONE | — | Uses JSON files in /tmp only |
File Tree
14 files · 39.9 KB · 1214 lines Shell 7f · 567L
Markdown 3f · 353L
Python 3f · 285L
JSON 1f · 9L
├─
▾
references
│ └─
▾
patches
│ ├─
generic.md
Markdown
│ └─
qqbot.md
Markdown
├─
▾
scripts
│ ├─
apply-qqbot-patch.sh
Shell
│ ├─
detect-language.py
Python
│ ├─
install.sh
Shell
│ ├─
lang-filter.py
Python
│ ├─
msg-queue.py
Python
│ ├─
reset-work-state.sh
Shell
│ ├─
smart-status-report.sh
Shell
│ ├─
status-query-daemon.sh
Shell
│ ├─
supervisor.sh
Shell
│ └─
update-work-state.sh
Shell
├─
_meta.json
JSON
└─
SKILL.md
Markdown
Dependencies 2 items
| Package | Version | Source | Known Vulns | Notes |
|---|---|---|---|---|
langdetect | * | pip | No | Version not pinned - update to: langdetect==1.0.9 |
inotify-tools | system | apt | No | System package for file monitoring |
Security Positives
✓ All file operations are confined to /tmp and documented skill directory
✓ No credential harvesting or sensitive path access detected
✓ No external network connections or data exfiltration
✓ Configuration stored locally, not transmitted externally
✓ Source file modifications are documented in apply-qqbot-patch.sh
✓ Backup of original files created before patching
✓ Lock file mechanism prevents duplicate daemon instances
✓ No base64 obfuscation or suspicious shell patterns