Skills/Glama/cad-eye-mcp

cad-eye-mcp@1.0.0

CAUTION· not started

Publisher claims: "Enables an AI to open and operate a CAD viewer for DXF, DWG, and Gerber/Excellon files, zooming, panning, clicking entities, toggling layers, and measuring while receiving updated screens and exact drawing data." Observed in sandbox: sends data to release-assets.githubusercontent.com.

Registry GlamaPublisher trajis-tech · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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 githubusercontent.com, autodesk.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · contacted release-assets.githubusercontent.com (undeclared)
What we could not test
server startup · the tool list · tool behavior

Find out what these hosts are first. In the honeypot it contacted release-assets.githubusercontent.com, which nothing in the package names as its own. If that is the vendor's service, fine; if you cannot place it, do not connect it.

$vet-skills run --net release-assets.githubusercontent.com -- <the server's command>

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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-12 and scored it 67/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to release-assets.githubusercontent.com.

Behavior trace

Honeypot run · 1 s · 3 scenarios
t+CategoryObserved action
0.3snetworkCONNECT tcp://github.com:443
0.3snetworkCONNECT tcp://release-assets.githubusercontent.com:443 · not in the allow-list, refused
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /usr/bin/uname
0.3sprocessexec /usr/bin/awk
0.3sprocessexec /usr/bin/mkdir
0.3sprocessexec /usr/bin/basename
0.3sprocessexec /usr/bin/curl
0.3sprocessexited 22: curl: (22) The requested URL returned error: 403
0.4sprocessdependency install exit 1 ·
0.4sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.4sprocessscript backend runs setup only
0.5sprocesssecond launch, clock +45 days, CI unset
0.7snetworkCONNECT tcp://github.com:443
0.7snetworkCONNECT tcp://release-assets.githubusercontent.com:443 · not in the allow-list, refused
0.7sprocessexec /usr/bin/dirname
0.7sprocessexec /usr/bin/uname
0.7sprocessexec /usr/bin/awk
0.7sprocessexec /usr/bin/mkdir
0.7sprocessexec /usr/bin/basename
0.7sprocessexec /usr/bin/curl
0.7sprocessexited 22: curl: (22) The requested URL returned error: 403

Static findings

MEDIUM
Python subprocess execution detectedscripts/try_tools.py:24 · Python subprocess execution detectedproc = subprocess.Popen([sys.executable, "-I", "-m", "cad_eye_mcp"], stdin=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/cad_eye_mcp/selfcheck.py:28 · Python subprocess execution detectedout = subprocess.run([str(exe), "--version"], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/cad_eye_mcp/cadcraft.py:58 · Python subprocess execution detectedself._proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/install_runtime.py:81 · Python subprocess execution detectedreturn subprocess.call([sys.executable, "-I", "-m", "cad_eye_mcp", "--check"], env=dict(os.environ))Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈36 tok
1 file · 33 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

13 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim trajis-tech: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim trajis-techPropose a patch to the maintainer