Skills/ClawHub/mind-wander

mind-wander@0.1.0

CAUTION· static only

Publisher claims: "Background reasoning agent that autonomously explores open questions using a local LLM (Qwen3.5-9B), a private knowledge graph for dead-end tracking, and Per..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher jebadiahgreenwood · publishing for 230 daysInstalls 799Last detonated 5 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Says it makes no network calls; the code sends requests to an outside host. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Python exec or eval of computed codescripts/tools.py:233 · Python exec or eval of computed code"open(", "os.system", "os.popen", "eval(", "exec(",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File permission modification commandscripts/install.sh:90 · File permission modification command — agent changes file ownership/permissionsrun chmod +x "$MW_DIR/install.sh" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Says it makes no network calls; the code sends requests to an outside hostscripts/install.sh:75 · Says it makes no network calls; the code sends requests to an outside host (stated in its description)run curl -sS https://bootstrap.pypa.io/get-pip.py -o /tmp/get-pip.pyFix: Declare and request only the permissions the task needs.
AST02
LOW
URL to a private-network addressscripts/install.sh:19 · URL to a private-network address — a LAN or development targetOLLAMA_URL="${OLLAMA_URL:-http://172.18.0.1:11436}"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addressSKILL.md:111 · URL to a private-network address — a LAN or development targetWANDER_OLLAMA = "http://172.18.0.1:11436"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addressscripts/mind_wander_config.py:14 · URL to a private-network address — a LAN or development targetWANDER_OLLAMA = os.environ.get("WANDER_OLLAMA", "http://172.18.0.1:11436")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addressscripts/install.sh:9 · URL to a private-network address — a LAN or development target# --ollama-url URL Ollama endpoint (default: http://172.18.0.1:11436)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/tools.py:257 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/install.sh:187 · Python subprocess execution detected… "message": f"Run mind-wander. Write /tmp/mw.py: import subprocess,sys\\nr=subprocess.run([sys.executable,'$MW_DIR/run.py','--model','$MODEL_VARIANT'],capture_output=True…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,210 tok
1 file · 12 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jebadiahgreenwood: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Says it makes no network calls; the code sends requests to an outside host≈ +4 on the totalDeclare and request only the permissions the task needs.
  3. Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. URL to a private-network address≈ +1 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jebadiahgreenwoodPropose a patch to the maintainer