Scan Report
5 /100
AutoThink
Automatically adjust OpenClaw's thinking level based on message complexity with persistent session mode switching
AutoThink is a legitimate, dependency-free thinking-mode manager that safely spawns the openclaw binary with no malicious indicators.
Safe to install
No action needed. The skill is safe to use as designed.
Findings 2 items
| Severity | Finding | Location |
|---|---|---|
| Info | Version string inconsistency Doc Mismatch | skill.json:3 |
| Info | spawn with shell:true in CLI RCE | src/cli.js:29 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Shell | NONE | WRITE | ✓ Aligned | cli.js:29 — spawns 'openclaw' binary with documented flags; this is the skill's … |
| Filesystem | NONE | NONE | — | No filesystem access found in any source file |
| Network | NONE | NONE | — | No network requests found |
| Environment | NONE | NONE | — | process.env only read for OPENCLAW_SESSION_ID and AUTOTHINK_DEBUG, no secret enu… |
| Skill Invoke | READ | READ | ✓ Aligned | Engine exposes processMessage/analyzeComplexity as documented API |
| Clipboard | NONE | NONE | — | No clipboard access |
| Browser | NONE | NONE | — | No browser access |
| Database | NONE | NONE | — | No database access |
File Tree
9 files · 27.6 KB · 1110 lines Markdown 3f · 486L
JavaScript 3f · 486L
JSON 3f · 138L
├─
▾
src
│ ├─
cli.js
JavaScript
│ ├─
hook.js
JavaScript
│ └─
index.js
JavaScript
├─
_meta.json
JSON
├─
DESIGN_V2.md
Markdown
├─
package.json
JSON
├─
README.md
Markdown
├─
skill.json
JSON
└─
SKILL.md
Markdown
Security Positives
✓ Zero external dependencies — no supply chain attack surface
✓ No credential harvesting or sensitive file/path access
✓ No network requests or data exfiltration
✓ No obfuscation, base64-encoded code, or anti-analysis techniques
✓ All subprocess execution is intentional (spawning openclaw) and documented
✓ Clean in-memory state management with no persistence to disk
✓ No hidden functionality — all behavior is readable in source files