dwg-mcp@r1
CAUTION· install onlyPublisher claims: "Enables AI agents to read, cluster, translate, and rewrite text in AutoCAD 2022–2027 drawings, handle Unicode fonts and height scaling, and execute code against the drawing database through a local gateway." 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 code
- 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 dwg-mcp@r1 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 2026-11-12 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: README directs the reader to a committed installer; README links to an external installer; Instructs the agent to modify its persistent memory or instruction files. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
Invoke-WebRequest "https://github.com/bimwright/dwg-mcp/releases/download/$tag/DwgMcp.Setup-$tag-win-x64.zip" -OutFile $zipFix: Pin versions and sources; vendor anything fetched at install time.https://github.com/bimwright/dwg-mcp/releases/download/$tag/DwgMcp.Setup-$tag-win-x64.zipFix: Pin versions and sources; vendor anything fetched at install time.…and affected clients with the user's involvement; do not save/close drawings or kill processes automatically. Restore backups on upgrade failure instead of uninstall…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# AGENTS.md — dwg-mcp health and update contractFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- README directs the reader to a committed installer≈ +9 on the totalPin versions and sources; vendor anything fetched at install time.
- Unclaimed publisher≈ +8 on the totalClaim bimwright: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.