Skills/ClawHub/clawbrain

clawbrain@0.1.15

CAUTION· static only

Publisher claims: "Claw Brain - Personal AI Memory System for OpenClaw/ClawDBot. Provides memory, personality, bonding, and learning capabilities with encrypted secrets support..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher clawcolab · publishing for 253 daysInstalls 4,757Last detonated 20 min 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 2026-11-22 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Privileged sudo command; Privileged sudo command. 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

HIGH
Privileged sudo commandSKILL.md:55 · Privileged sudo command — agent may execute with elevated privileges- ❌ **No sudo required** - All operations in your home directoryFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:147 · Privileged sudo command — agent may execute with elevated privilegessudo tee /etc/systemd/system/clawdbot.service.d/brain.conf << EOFFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageSECURITY.md:228 · Authorization escalation language · informational: not an instruction file❌ **Root Access**: If attacker has root, they can read the key fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageSECURITY.md:75 · Authorization escalation language · informational: not an instruction file- Require sudo or root accessFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandSKILL.md:197 · File permission modification command — agent changes file ownership/permissions- 🔐 Encryption key stored at `~/.config/clawbrain/.brain_key` (chmod 600)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandSKILL.md:133 · Privileged sudo command — agent may execute with elevated privileges# Add to ~/.bashrc or ~/.zshrc (no sudo required)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:145 · Privileged sudo command — agent may execute with elevated privilegessudo mkdir -p /etc/systemd/system/clawdbot.service.dFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageSECURITY.md:24 · Authorization escalation language · informational: not an instruction file**Core installation and operation never require root privileges:**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandSKILL.md:91 · Privileged sudo command — agent may execute with elevated privilegessudo systemctl restart clawdbot # or openclawFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,447 tok
1 file · 3 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

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim clawcolab: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim clawcolabPropose a patch to the maintainer