Skills/PyPI/reachy-mini-mcp

reachy-mini-mcp@0.3.0

CAUTION· not started

Publisher claims: "MCP server + manager CLI for the Reachy Mini robot." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher agentculture · publishing for 166 daysInstalls 72Last detonated 1 h 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 sonarcloud.io — 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 reachy-mini-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 2026-11-15 and scored it 75/100 (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; Refusal suppression; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexec /usr/bin/awk
0.0sprocessexited 1:
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
0.3sprocessexec /usr/bin/awk
0.3sprocessexited 1:

Static findings

MEDIUM
File type combined with upload actionCLAUDE.md:144 · File type combined with upload action — agent may exfiltrate local data files…'s persona / system prompt for the LLM driving `operate_robot`. - `dance_moves/*.json` — despite the `.json` extension these are **captured LLM debug transcripts** (example `operate_robot` command sequences with parse logs), not structured…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 pathsreachy_mini_mcp/cli/_commands/doctor.py:98 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv = Path.cwd() / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsdocker-compose-vllm.yml:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Refusal suppression.claude/skills/cicd/SKILL.md:173 · Refusal suppression — attempting to prevent safety responsesto a later PR, don't refuse).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsreachy_mini_mcp/tts_queue.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load environment variables from .env file if availableFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsdocker-compose-vllm.yml:63 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsreachy_mini_mcp/server.py:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsstart_openai_server.sh:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif [ ! -f .env ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsreachy_mini_mcp/server_openai.py:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsCLAUDE.md:125 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files… the vLLM containers) that then calls `/execute_tool`. ## Configuration Copy `.env.example` (MCP/TTS) or `.env.openai.example` (HTTP/LLM) to `.env`. `.env` is git…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 pathsreachy_mini_mcp/_runtime.py:23 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load .env here, before REACHY_BASE_URL is captured below. Both servers alsoFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsstart_openai_server.sh:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescp .env.openai.example .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandsetup.sh:33 · Privileged sudo command — agent may execute with elevated privilegesecho " - Linux: sudo apt install git-lfs"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsreachy_mini_mcp/cli/_commands/doctor.py:103 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesparts.append(f".env present ({dotenv})")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 pathsstart_openai_server.sh:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "⚠️ No .env file found"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsdocker-compose-vllm.yml:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- HF_TOKEN=${HF_TOKEN} # Set your Hugging Face token in .env file or export itFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsstart_openai_server.sh:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Check if .env file existsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsstart_openai_server.sh:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho " Creating from .env.openai.example..."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 pathsreachy_mini_mcp/_runtime.py:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# otherwise run before their load_dotenv() and ignore a .env-defined base URL.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_mcp_entry.py:22 · MCP server using network transport (SSE/HTTP) — data sent over networkassert cfg["mcpServers"]["robot"]["env"]["REACHY_BASE_URL"] == "http://example:9000"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandshutdown_daemon.sh:22 · Process kill command — agent can terminate processesif ! kill -0 $DAEMON_PID 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandshutdown_daemon.sh:18 · Process kill command — agent can terminate processeskill -TERM $DAEMON_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandshutdown_daemon.sh:33 · Process kill command — agent can terminate processeskill -KILL $DAEMON_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_cli_dispatch.py:69 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandshutdown_daemon.sh:31 · Process kill command — agent can terminate processesif kill -0 $DAEMON_PID 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedreachy_mini_mcp/tts_queue.py:191 · Python subprocess execution detectedself.current_process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandshutdown_daemon.sh:30 · Process kill command — agent can terminate processes# If still running after 10 seconds, force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_doctor.py:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesmonkeypatch.chdir(tmp_path) # no .env here, so only env vars contributeFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_cli_smoke.py:114 · Python subprocess execution detectedresult = subprocess.run([sys.executable, "-c", code], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_doctor.py:74 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env").write_text("X=1\n", encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsdocker-compose-vllm.yml:72 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- HF_TOKEN=${HF_TOKEN} # Set your Hugging Face token in .env file or export itFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedreachy_mini_mcp/tts_queue.py:119 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_doctor.py:77 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert ".env present" in doctor._env_check().detailFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedreachy_mini_mcp/tts_queue.py:249 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈24,541 tok
14 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

No advisories in OSV for reachy-mini-mcp@0.3.0 as of 45 min ago. This is the package itself, not its dependencies.

What would make this Verified

5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim agentculture: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
  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 agentculturePropose a patch to the maintainer