Skills/npm/blender-skill

blender-skill@0.31.1

VERIFIED· startup only

Publisher claims: "Agent Skill that gives coding agents (Claude Code, Cursor, Codex) a local 3D asset pipeline: inspect, convert, optimize, render, bake and validate glb/gltf/fbx/obj/stl/usd/usdz/ply/abc/.blend files via headless Blender. No API keys, no cloud, no pip depen" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher kajisho5 · publishing for 78 daysInstalls 242Last detonated 22 min ago
$claude mcp add blender-skill -- npx -y blender-skill
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What changed since 0.31.0

vet-skills diff blender-skill 0.31.0 0.31.1

This version reaches for something 0.31.0 did not: 6 new hosts (apple.com, blender.org, khronos.org, roblox.com, …). Compared from the two recorded runs, not from source.

New hosts
apple.com, blender.org, khronos.org, roblox.com, sketchfab.com, vrchat.com

0.31.0 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-20 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimedstartup only: exited (0) before answering · installed Claude Code: /tmp/ks-detonate-RU9JM1/task/home/.claude/skills/blender-skill Done. Ask your agent things like "decimate this model to 50k triangles" or "check this glb for Unity".
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/_render_output.py:239 · Python subprocess execution detectedproc = subprocess.run([ffprobe, "-v", "error", "-select_streams", "v:0", "-show_entries",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmcp/server.py:76 · Python subprocess execution detectedproc = subprocess.run([sys.executable, str(script)] + argv, 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 detectedscripts/_run.py:98 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/_contract.py:87 · Python subprocess execution detectedout = subprocess.run([binary, "--version"], capture_output=True, text=True, timeout=60).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/_delegate.py:42 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/batch.py:60 · Python subprocess execution detectedproc = subprocess.run(argv, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagebin/install.js:12 · npx invocation of non-well-known package — may execute untrusted code* npx blender-skill --dir ./skills # custom parent directoryFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:11 · npx invocation of non-well-known package — may execute untrusted code* npx blender-skill --all # all of the aboveFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/scene.py:2 · File type combined with upload action — agent may exfiltrate local data files"""Assemble a declarative scene.json (asset placement, lights, camera, background, output)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/dev/roadmap_to_issues.py:58 · Python subprocess execution detectedproc = subprocess.run(["gh", "issue", "create", "--title", title, "--label", labels, "--body", body],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagebin/install.js:10 · npx invocation of non-well-known package — may execute untrusted code* npx blender-skill --codex # Codex (~/.agents/skills/blender-skill)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/dev/roadmap_to_issues.py:53 · Python subprocess execution detectedexisting = subprocess.run(["gh", "issue", "list", "--search", f'in:title "{title}"', "--json", "title"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagebin/install.js:9 · npx invocation of non-well-known package — may execute untrusted code* npx blender-skill --cursor # Cursor (~/.cursor/skills/blender-skill)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/verify.py:24 · Python subprocess execution detectedproc = subprocess.run(argv, 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 detectedscripts/fit.py:142 · Python subprocess execution detectedproc = subprocess.run(argv, capture_output=True, text=True, timeout=args.timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagebin/install.js:8 · npx invocation of non-well-known package — may execute untrusted code* npx blender-skill # Claude CodeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/dev/roadmap_to_issues.py:43 · Python subprocess execution detectedsubprocess.run(["gh", "label", "create", label], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈5,491 tok
1 file · 45 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

Not checked against OSV yet; the weekly check has not reached this version.

blender-skill@0.31.1 safety verdict: Verified (startup only) — KillerSkills