swiss-environment-mcp@0.7.0
CAUTION· not startedPublisher claims: "MCP Server für Schweizer Umweltdaten des BAFU – Luft, Wasser, Naturgefahren und Umweltindikatoren" 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 codeAlso admin.ch, opendata.swiss, waldbrandgefahr.ch, slf.ch, jagdstatistik.ch, shields.io, cube.link, purl.org, naturgefahren.ch — not the publisher's domain; check what for before connecting.
- 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 [email protected] 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 2026-11-19 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: Tool poisoning; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
modul = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.1. eingebettete System-Prompts / Instruktionen in Tool-Descriptions,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""`MCPServer` lehnt einen unbekannten Schluessel schon im Konstruktor ab;Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.sudo install /tmp/gitleaks /usr/local/bin/gitleaksFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# --- TOOLS: FLUGLÄRM / BAZL-LÄRMBELASTUNGSKATASTER ----------------------------Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(modul)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.RUN pip install --no-cache-dir "$(ls /tmp/*.whl)[otel]" && rm -rf /tmp/*.whlFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.2. Override-/Jailbreak-Phrasen («ignore previous instructions» u. ä.),Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.BafuDatasetDetailInput(dataset_id="../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.2. Override-/Jailbreak-Phrasen («ignore previous instructions» u. ä.),Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.pytest -m live -v --junitxml=live-report.xml 2>&1 | tee live-output.txtFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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
No advisories in OSV for swiss-environment-mcp@0.7.0 as of 18 h 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%- Tool poisoning≈ +9 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Unclaimed publisher≈ +8 on the totalClaim malkreide: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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.
- Privileged sudo command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.