Skills/PyPI/mifblender-mcp

mifblender-mcp@1.3.1

CAUTION· static only

Publisher claims: "AI in Blender through MCP: 428 typed tools that check their parameters and read the result back. Free, source available." Observed in sandbox: static analysis only — behavior not yet observed.

Registry PyPI (MCP server)Publisher mifsopo1 · publishing for 5 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

It will ask for
MIFBLENDER_TOKENConfiguration, not credentials: MIF_BLENDER_ARTIFACTS, MIF_BLENDER_ARTIFACTS_FILE, MIF_BLENDER_JOURNAL, MIF_BLENDER_LISTENERS, MIF_BLENDER_UNDO, MIF_CHANGE_CAP, MIF_CHILD_JOB_MEMORY_GB, MIF_CHILD_JOBS_DIR, MIF_COMFY_HOST, MIF_EXTENSIONS, MIF_EXTENSIONS_DIR, MIF_MAX_CHILD_JOBS, MIFBLENDER_ACTION, MIFBLENDER_MARK, MIFBLENDER_MODULE, MIFBLENDER_ZIP, XDG_STATE_HOME
Where it talks to
no vendor host named in the codeAlso mifshowcase.store — not the publisher's domain; check what for before connecting.
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

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 analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Destructive file system command detected. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Access to sensitive file pathssrc/mifblender_mcp/setup_cli.py:142 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesm = re.search(r'(?m)^\[mcp_servers\.%s\.env\]\s*\n(?:.*\n)*?MIF_BLENDER_TOKEN = "([^"]+)"' % SERVER_NAME, fh.read())Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Refusal suppressionsrc/mifblender_mcp/mcp-server/packs.json:311 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file…imitive, bl_create_curve, bl_create_text, bl_create_empty and bl_create_lattice never refuse a taken name: the new object becomes Name.001 (nameWasSuffixed: true). Use the …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Refusal suppressionsrc/mifblender_mcp/mcp-server/packs.json:691 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file…t_light", "bl_set_light_shadow" ] }, { "rule": "Blender never refuses a taken name: re-running bl_create_light or bl_create_camera adds a .001 copy …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/blender-addon/MifBlender/ops_gamebake.py:709 · Python subprocess execution detectedpopen = subprocess.Popen([exe, "-b", blend, "--factory-startup", "--python", script],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/setup_cli.py:156 · Python subprocess execution detectedsubprocess.run([claude, "mcp", "remove", "--scope", "user", SERVER_NAME], capture_output=True, text=True, **HIDE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/blender-addon/MifBlender/ops_render.py:1804 · Python subprocess execution detectedpopen = subprocess.Popen(argv, **childproc.hidden(dict(stdout=log_fh, stderr=subprocess.STDOUT,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/setup_cli.py:249 · Python subprocess execution detectedr = subprocess.run([exe, "--version"], capture_output=True, text=True, timeout=60, **HIDE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/setup_cli.py:160 · Python subprocess execution detectedr = subprocess.run(cmd + ["--", command] + args, capture_output=True, text=True, **HIDE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/setup_cli.py:195 · Python subprocess execution detectedr = subprocess.run([claude, "mcp", "remove", "--scope", "user", SERVER_NAME], capture_output=True, text=True, **HIDE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedsrc/mifblender_mcp/blender-addon/MifBlender/ops_pose.py:689 · Destructive file system command detected"are of the format \"UUID:catalog/path/for/assets:simple catalog name\"\n\nVERSION 1\n\n")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/setup_cli.py:163 · Python subprocess execution detectedgot = subprocess.run([claude, "mcp", "get", SERVER_NAME], capture_output=True, text=True, **HIDE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mifblender_mcp/blender-addon/MifBlender/childproc.py:464 · Python subprocess execution detectedproc = subprocess.Popen(args, **hidden(popen_kwargs))Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/mifblender_mcp/blender-addon/MifBlender/ops_handoff.py:612 · Process kill command — agent can terminate processes"""Why Unreal's groom builder cannot take this hair, or None. These kill the EDITOR, in the engine's own voxelizer, whichFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mifblender_mcp/blender-addon/MifBlender/ops_scene.py:829 · Process kill command — agent can terminate processesNOT kill the connection. Names persist from call to call, as in a console,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mifblender_mcp/blender-addon/MifBlender/ops_render.py:1952 · Process kill command — agent can terminate processesout["job"] = job["watch"].report() # the tree's peak memory, the ceiling, and a kill past itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈67 tok
1 file · 81 in bundle

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 mifblender-mcp@1.3.1 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim mifsopo1: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mifsopo1Propose a patch to the maintainer