easee-mcp@r1
CAUTION· not startedPublisher claims: "Enables voice queries about an Easee car charger's charging status, current limit, recent sessions, and energy use, with strictly read-only access that cannot start, stop, or modify the charger." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- 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 code
- What we saw when it ran
- 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.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is easee-mcp@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-22 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
not run: the workflow runs each of these; nesting them here would run the suite inside itselfFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.result = subprocess.run( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.not run: these are the gates; running them from inside a gate would recurseFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.not run: it installs; the suite runs inside what it installsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.not run: it needs claude-voice and this checkout's pathFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.not run: it asks for the loginFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.not run: it reads the owner's own login, which no test may doFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.not run: clones the repository the reader is already inFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.not run: it asks for typed inputFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.not run: whyFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.not run: it is already on in this cloneFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.hangs even so is ended by hand, with its whole group, by `kill -9 -- -<its pid>`. ItsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.step = subprocess.Popen( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# turns colour back on, which would otherwise make every kill unattributable.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.done = subprocess.run(["git", *args], cwd=ROOT, capture_output=True, text=True, check=True) # noqa: S603, S607Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f" `chmod 700 {folder}` and log in again."Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.found = subprocess.run( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f"Stopping {command[0]} and waiting for it; if it hangs: kill -9 -- -{step.pid}\n"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.assert "chmod 700" in errFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.with subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# A kill by some other test is not evidence about this rule.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.A kill is not enough on its own. A mutation breaks whatever it breaks, and itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.module = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
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
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim roykollensvendsen: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.