notebook-editor-mcp@0.1.2
CAUTION· install onlyPublisher claims: "Local Jupyter notebook editor an MCP client drives, with a browser tab watching the same session" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
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 react.dev — 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
- use of the skill by an agent
Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Bidirectional text override characters detected; Hidden zero-width characters detected; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
…on");const r=await fetch(`${Wt}${e}`,{...n,headers:s});if(!r.ok){const l=await r.json().catch(()=>null);throw new _e(r.status,l?.error??{code:"request_failed",message:r.statusText||"Request failed",details:{}})}if(r.status!==204)return r.j…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.realises that halfway through needs a way out that is not "kill theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…const uo=/x/.unicode!=null?"gu":"g",om=new RegExp(`[\0-\b --\u2028\u2029\uFEFF-]`,uo),lm={0:"null",7:"bell",8:"backspace",10:"newline",11:"vertica…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.…d:u})}}return t}}const uo=/x/.unicode!=null?"gu":"g",om=new RegExp(`[\0-\b --\u2028\u2029\uFEFF-]`,uo),lm={0:"null",7:"bell",8:"backspace",10:"new…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.(re.compile(r"(?i)(?:\.env\b|dotenv\b|\.pem\b|\.key\b|\.ssh\b|credentials?|\.aws/|\.config/gcloud)"), "credential_access", "Accesses secrets or credentials"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.name of the same spelling. Rejecting on that would kill a perfectly goodFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…nstable_NormalPriority,M1=D.unstable_LowPriority,hi=D.unstable_IdlePriority,D1=D.log,U1=D.unstable_setDisableYieldValue,Ma=null,Fl=null;function Wt(l){if(typeof D1=="function"&&U1(l),Fl&&typeof Fl.setStrictMode=="function")try{Fl.setStrict…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.probe = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…fect(()=>{if(ce&&!ei){var Ze={doc:e,selection:t,extensions:Ci},Lt=Z?I.fromJSON(Z.json,Ze,Z.fields):I.create(Ze);if(_s(Lt),!_){var zt=new C({state:Lt,parent:ce,root:ye});Ne(zt),r&&r(zt,Lt)}}return()=>{_&&(_s(void 0),Ne(void 0))}},[ce,ei]),x…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for notebook-editor-mcp@0.1.2 as of 26 h ago. This is the package itself, not its dependencies.
What would make this Verified
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim aglyx3: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Bidirectional text override characters detected≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- 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.
- 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.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.