Scan Report
5 /100
command-guardian
Preflight safety guard for shell and infrastructure commands
Command Guardian is a legitimate preflight safety analyzer for shell commands. It performs read-only risk analysis and does not execute analyzed commands or exhibit any malicious behavior.
Safe to install
This skill is safe for use. The dangerous shell patterns (curl|sh, wget|bash) referenced in documentation are documented as dangerous patterns TO FLAG, not patterns the skill performs itself.
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | READ | READ | ✓ Aligned | agents/openai.yaml declares filesystem:READ |
| Shell | WRITE | WRITE | ✓ Aligned | guardlib.py:294-297 uses subprocess for git commands only |
| Environment | NONE | READ | ✓ Aligned | guardlib.py:76 uses os.path.expandenv() for path resolution only |
| Network | NONE | NONE | — | No network calls found |
| Skill Invoke | NONE | NONE | — | No skill invocation found |
| Clipboard | NONE | NONE | — | No clipboard access found |
| Browser | NONE | NONE | — | No browser access found |
| Database | NONE | NONE | — | No database access found |
2 Critical 2 findings
Critical Dangerous Command 危险 Shell 命令
curl | sh SKILL.md:54 Critical Dangerous Command 危险 Shell 命令
wget | bash references/tool-patterns.md:30 File Tree
11 files · 45.5 KB · 1208 lines Python 7f · 1007L
Markdown 3f · 193L
YAML 1f · 8L
├─
▾
agents
│ └─
openai.yaml
YAML
├─
▾
references
│ ├─
risk-rules.md
Markdown
│ └─
tool-patterns.md
Markdown
├─
▾
scripts
│ ├─
classify_command.py
Python
│ ├─
guardlib.py
Python
│ ├─
path_guard.py
Python
│ ├─
preflight.py
Python
│ ├─
rollback_hints.py
Python
│ └─
secret_guard.py
⚠
Python
├─
▾
tests
│ └─
test_powershell_risk.py
Python
└─
SKILL.md
Markdown
Security Positives
✓ Skill performs read-only command analysis without executing analyzed commands
✓ Subprocess usage limited to git context (git rev-parse, git status) - legitimate for security tooling
✓ No credential harvesting or exfiltration - only detects inline secrets to warn about them
✓ No network requests or data exfiltration channels
✓ No obfuscation techniques (no base64, no eval, no atob)
✓ No access to sensitive paths (~/.ssh, ~/.aws, .env)
✓ No persistence mechanisms (no cron, no startup hooks, no backdoors)
✓ Capabilities properly declared in agents/openai.yaml
✓ Comprehensive test suite validates expected security behaviors
✓ Dangerous patterns (curl|sh, wget|bash) are documented AS PATTERNS TO FLAG, not as behaviors exhibited