Skills/PyPI/brain-core-mcp

brain-core-mcp@0.4.18

CAUTION· not started

Publisher claims: "A memory for your Claude Code agent that survives the session: one local MCP server, five tools, a markdown vault, an eval." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher xy-claude · publishing for 13 daysInstalls 5,229Last detonated 5d ago
What would fix thisWatchDispute verdict

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

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso githubusercontent.com, astral.sh, nodejs.org — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx brain-core-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

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 2026-11-09 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Direct script execution from GitHub raw URL; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexited 2: usage: install.sh --agent NAME [--user Alex] [--dir PATH] [--provider anthropic|openai|claude-code] [--api-key-env VAR] [--profile DIR] [--lite] [--dashboard] [--desktop] [--ref TAG]
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.2sprocessexited 2: usage: install.sh --agent NAME [--user Alex] [--dir PATH] [--provider anthropic|openai|claude-code] [--api-key-env VAR] [--profile DIR] [--lite] [--dashboard] [--desktop] [--ref TAG]

Static findings

MEDIUM
Remote installer piped to shellsrc/brain_core/installer.py:219 · Remote installer piped to shellraise RuntimeError("uv is required: curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
CRITICAL
Pipe-to-shell patterninstall.sh:4 · Pipe-to-shell pattern — downloads and immediately executes remote code…rain-core one-line installer (macOS and Linux; Windows uses install.ps1). # # curl -fsSL https://raw.githubusercontent.com/xy-claude/brain-core/main/install.sh | bash -s -- --agent NAME [--user Alex] [--dir ~/Agents/NAME] [--provider anthr…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Direct script execution from GitHub raw URLinstall.sh:4 · Direct script execution from GitHub raw URL — unverified code source…ne-line installer (macOS and Linux; Windows uses install.ps1). # # curl -fsSL https://raw.githubusercontent.com/xy-claude/brain-core/main/install.sh | bash -s -- --agent NAME [--user Alex] [--dir ~/Agents/NAME] [--provider anthr…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/brain_core/cron.py:459 · Python subprocess execution detectedcp = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patterninstall.sh:55 · Pipe-to-shell pattern — downloads and immediately executes remote codeif have uv; then echo "present"; else curl -LsSf https://astral.sh/uv/install.sh | sh; fiFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedsrc/brain_core/installer.py:137 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Direct script execution from GitHub raw URLinstall.sh:43 · Direct script execution from GitHub raw URL — unverified code source/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/brain_core/distill.py:149 · Python subprocess execution detectedjs = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/cron.py:567 · Python subprocess execution detectedsubprocess.run(["crontab", "-"], input=merged, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/cron.py:596 · Python subprocess execution detectedreturn subprocess.run(["schtasks", "/Query", "/TN", task], capture_output=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/distill.py:141 · Python subprocess execution detectedmd = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/installer.py:148 · Python subprocess execution detectedsubprocess.run(["powershell", "-NoProfile", "-Command", stop], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellinstall.sh:4 · Remote installer piped to shell…rain-core one-line installer (macOS and Linux; Windows uses install.ps1). # # curl -fsSL https://raw.githubusercontent.com/xy-claude/brain-core/main/install.sh | bash -s -- --agent NAME [--user Alex] [--dir ~/Agents/NAME] [--provider anthr…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsrc/brain_core/distill.py:203 · Python subprocess execution detectedinfo = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/cron.py:565 · Python subprocess execution detectedcp = subprocess.run(["crontab", "-l"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/cron.py:642 · Python subprocess execution detectedsubprocess.run(cmd, capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/cli/main.py:294 · Python subprocess execution detectedcp = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedDockerfile:14 · Destructive file system command detectedRUN pip install --no-cache-dir . && rm -rf /srcFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellinstall.sh:55 · Remote installer piped to shellif have uv; then echo "present"; else curl -LsSf https://astral.sh/uv/install.sh | sh; fiFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
CRITICAL
Pipe-to-shell patternsrc/brain_core/installer.py:219 · Pipe-to-shell pattern — downloads and immediately executes remote coderaise RuntimeError("uv is required: curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Process kill commandsrc/brain_core/recall.py:130 · Process kill command — agent can terminate processesexcept Exception as e: # a dead store must not kill recallFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/installer.py:220 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/brain_core/templates/agent/.claude/hooks/block-dangerous-bash.sh:68 · File permission modification command — agent changes file ownership/permissionsblock "chmod 777 grants world-writable permissions — use the least-permissive mode that works"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/brain_core/cli/main.py:57 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"""Write a whole agent: brain.yaml, CLAUDE.md, rules, skills, hooks, .mcp.json, vault."""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/brain_core/installer.py:256 · Python subprocess execution detectedsubprocess.run(["systemctl", "--user", "daemon-reload"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/brain_core/templates/agent/.claude/hooks/block-dangerous-bash.sh:66 · File permission modification command — agent changes file ownership/permissions# 5) chmod 777 on broad targetsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedsrc/brain_core/installer.py:152 · Python subprocess execution detectedsubprocess.Popen( # outlives this command; the Run key starts it again at the next logonFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,790 tok
4 files · 80 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim xy-claude: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  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. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim xy-claudePropose a patch to the maintainer