Skills/PyPI/central-mcp

central-mcp@0.21.0

CAUTION

Publisher claims: "Coding agent-agnostic MCP hub for managing multiple coding agents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher andy5090 · joined 0 days agoInstalls 1,092Last detonated 4 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-28 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Fake instruction boundary tag; Prompt injection. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/central-mcp
0.2sprocessexited 127: timeout: failed to run command '.venv/bin/central-mcp': No such file or directory
0.2sclaimedno tools/list reply (exit 127)
0.2sprocessscript backend runs setup only

Static findings

CRITICAL
Fake instruction boundary tagdocs/ROADMAP.md:227 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagREADME.md:182 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionsrc/central_mcp/data/CLAUDE.md:367 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagdocs/ROADMAP.ko.md:227 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagREADME.md:185 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagREADME.md:184 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagREADME.md:183 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionsrc/central_mcp/data/AGENTS.md:377 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Fake instruction boundary tagREADME.md:181 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandsrc/central_mcp/pty_sessions.py:10 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationCLAUDE.md:66 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Instructs the agent to modify its persistent memory or instruction filesREADME.md:259 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:289 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/central_mcp/install.py:428 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/install.py:449 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/adapters/base.py:719 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/central_mcp/quota/claude.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/central_mcp/quota/claude.py:100 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/pulse.py:71 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsAGENTS.md:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/install.py:142 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:791 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionsrc/central_mcp/data/AGENTS.md:62 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:587 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/central_mcp/adapters/base.py:577 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Authorization escalation languagesrc/central_mcp/data/CLAUDE.md:367 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languagesrc/central_mcp/data/AGENTS.md:377 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/central_mcp/orch_session.py:165 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/central_mcp/layout.py:403 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/install.py:153 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/central_mcp/dispatches_db.py:245 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/central_mcp/layout.py:402 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/central_mcp/quota/claude.py:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/adapters/base.py:153 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/quota/claude.py:74 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionsrc/central_mcp/tui/terminal.py:26 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/central_mcp/tasks_protocol.py:86 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/central_mcp/tmux.py:5 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/server.py:1002 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_pulse.py:154 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/tmux.py:24 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/zellij.py:49 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_note.py:111 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_pulse.py:169 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/upgrade.py:156 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_pulse.py:25 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_note.py:129 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/central_mcp/tui/terminal.py:205 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

What would make this Verified

27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Asks the agent to act silently or skip confirmation≈ +8 on the totalRemove "do not tell the user", "without asking", "disable safety" and similar. An agent skill should never ask to be invisible.
  3. Unclaimed publisher≈ +8 on the totalClaim andy5090: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  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. Process kill command≈ +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 andy5090