pedit-mcp@0.1.0
CAUTION· not startedPublisher claims: "Open-source AI image editor and MCP server: layers, masks, generative fill, image-to-image, background removal. A Photoshop/GIMP alternative an AI agent can drive, local or with your OpenAI, Gemini or Stability API key." 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
ANTHROPIC_AUTH_TOKENConfiguration, not credentials: PEDIT_CLAUDE, PEDIT_COMFY_URL, PEDIT_HOME, PEDIT_SEGNALAZIONI- Where it talks to
- no vendor host named in the codeAlso openrouter.ai, stability.ai, replicate.com, groq.com, mistral.ai, deepseek.com, x.ai, react.dev, metiu.xyz — 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 with a scoped credential, under the guard, and read the third-party hosts first. The code names openrouter.ai, stability.ai, replicate.com, groq.com, mistral.ai, deepseek.com, x.ai, react.dev, metiu.xyz as well as its own vendor. The guard injects ANTHROPIC_AUTH_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-14 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Base64 encoding combined with network call. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
assert f.json()["input"] == {"prompt": "a lighthouse", "aspect_ratio": "1:1", "output_format": "png", "seed": 3}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sub = mcp_server.mcp.streamable_http_app(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.…nstable_NormalPriority,Am=r.unstable_LowPriority,Gs=r.unstable_IdlePriority,Dm=r.log,Um=r.unstable_setDisableYieldValue,bn=null,Et=null;function _e(l){if(typeof Dm=="function"&&Um(l),Et&&typeof Et.setStrictMode=="function")try{Et.setStrict…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…"$~"&&e!=="$!"||l++;e=a}while(e)}function zh(l,t,e){if(t=CSS.escape(t)!==t?"r-"+btoa(t).replace(/=/g,""):t,l.style.viewTransitionName=t,e!=null&&(l.style.viewTransitionClass=e),e=getComputedStyle(l),e.display==="inline"){if(t=l.getClientRe…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…sx("span",{children:"Save as"}),c.jsx("input",{value:G,placeholder:`${m}${I}${b}.json (optional, enables autosave)`,onChange:F=>B(F.target.value)})]}),c.jsxs("div",{className:"modal-foot",children:[c.jsx("button",{onClick:s,children:"Cance…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.assert "input_image" in f.json()["input"]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.config_mcp = json.dumps({"mcpServers": {"pedit": {"type": "http", "url": mcp_url}}})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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 pedit-mcp@0.1.0 as of 47 min ago. This is the package itself, not its dependencies.
What would make this Verified
3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim metiutek: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
- Base64 encoding combined with network call≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- 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.