Skills/ClawHub/cognitive-brain

cognitive-brain@7.0.1

CAUTION· not started

Publisher claims: "Provides a cross-session AI memory and cognition system with four-layer memory, real-time sync, free thinking, intelligent prediction, and knowledge visualiz..." Observed in sandbox: calls github.com only, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher aboutyao · publishing for 252 daysInstalls 2,290Last detonated 1 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Destructive file system command detected. Summary: calls github.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 62 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.5sfilesystemread ~/.openclaw/workspace/skills/cognitive-brain/.git/config · ~/.openclaw/workspace/skills/cognitive-brain/.git/packed-refs · ~/.openclaw/workspace/skills/cognitive-brain/.git/HEAD · ~/.openclaw/workspace/skills/cognitive-brain/.git · ~/.openclaw/workspace/skills/cognitive-brain/.git/info · ~/.openclaw/workspace/skills/cognitive-brain/.git/refs outside project
0.5sfilesystemwrote ~/.openclaw/workspace/skills/cognitive-brain/.git/info/exclude · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/pre-rebase.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/push-to-checkout.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/fsmonitor-watchman.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/pre-applypatch.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/update.sample
0.5snetworkCONNECT tcp://github.com:443
0.5sprocessexec /usr/bin/cut
0.5sprocessexec /usr/bin/mkdir
0.5sprocessexec /usr/bin/git
0.5sprocessexec /usr/lib/git-core/git
0.5sprocessexec /usr/lib/git-core/git-remote-https
0.5sprocessexited 1:
0.5sprocessinstall script run in the sandbox
0.6snetworkCONNECT tcp://github.com:443
0.6sprocessexited 1: Node.js v22.23.5
61sprocessdependency install exceeded 60s
61sclaimednot started: dependency install timed out; the server itself was not observed
61sprocessscript backend runs setup only
61sprocesssecond launch, clock +45 days, CI unset
61sfilesystemread ~/.openclaw/workspace/skills/cognitive-brain/.git/config · ~/.openclaw/workspace/skills/cognitive-brain/.git/packed-refs · ~/.openclaw/workspace/skills/cognitive-brain/.git/HEAD · ~/.openclaw/workspace/skills/cognitive-brain/.git · ~/.openclaw/workspace/skills/cognitive-brain/.git/info · ~/.openclaw/workspace/skills/cognitive-brain/.git/refs outside project
61sfilesystemwrote ~/.openclaw/workspace/skills/cognitive-brain/.git/info/exclude · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/pre-rebase.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/push-to-checkout.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/fsmonitor-watchman.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/pre-applypatch.sample · ~/.openclaw/workspace/skills/cognitive-brain/.git/hooks/update.sample
61snetworkCONNECT tcp://github.com:443
61sprocessexec /usr/bin/cut
61sprocessexec /usr/bin/mkdir
61sprocessexec /usr/bin/git
61sprocessexec /usr/lib/git-core/git
61sprocessexec /usr/lib/git-core/git-remote-https
61sprocessexited 1:
62snetworkCONNECT tcp://github.com:443
62sprocessexited 1: Node.js v22.23.5

Static findings

MEDIUM
Remote installer piped to shellinstall.sh:4 · Remote installer piped to shell# 用法: curl -fsSL https://.../install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File type combined with upload actionscripts/core/entity_extractor.cjs:18 · File type combined with upload action — agent may exfiltrate local data filestech: /(?:[a-zA-Z][a-zA-Z0-9]*\.js|[a-zA-Z][a-zA-Z0-9]*\.py|[a-zA-Z][a-zA-Z0-9]*\.json|node|python|redis|postgres|docker|kubernetes|react|vue|angular|express|koa|django|flask)/gi,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/core/safety.cjs:139 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'/etc/passwd',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/core/safety.cjs:140 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'/etc/shadow',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedscripts/core/safety.cjs:422 · Destructive file system command detectednode safety.cjs scan "rm -rf /"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicescripts/core/safety.cjs:422 · Destructive command against a filesystem root or devicenode safety.cjs scan "rm -rf /"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patterninstall.sh:4 · Pipe-to-shell pattern — downloads and immediately executes remote code# 用法: curl -fsSL https://.../install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File type combined with upload actionscripts/tools/init-db.cjs:276 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('⚠️ pg 模块未安装,跳过 PostgreSQL 初始化');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/core/safety.cjs:363 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` 输入: ${input.slice(0, 50)}...`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/utils/logger.cjs:35 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/tools/init-db.cjs:284 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('📦 连接 PostgreSQL...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/tools/init-db.cjs:286 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('✅ PostgreSQL 连接成功\n');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,388 tok
1 file · 94 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

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

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. Unclaimed publisher≈ +8 on the totalClaim aboutyao: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  5. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim aboutyaoPropose a patch to the maintainer