mind-wander@0.1.0
CAUTION· static onlyPublisher 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.
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 onlyThis 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
"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.run chmod +x "$MW_DIR/install.sh" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.run curl -sS https://bootstrap.pypa.io/get-pip.py -o /tmp/get-pip.pyFix: Declare and request only the permissions the task needs.OLLAMA_URL="${OLLAMA_URL:-http://172.18.0.1:11436}"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.WANDER_OLLAMA = "http://172.18.0.1:11436"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.WANDER_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.# --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.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.… "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.Cost to the agent
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%- 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.
- 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.
- 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.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- URL to a private-network address≈ +1 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.