ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Blender Mcp

v1.0.0

Advanced bridge to Blender via MCP. Allows querying scene, creating objects, applying materials, and running custom BPY code in real-time.

⭐ 0· 459·4 current·4 all-time
by@flayzz
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
The name/description (Blender MCP bridge) matches the implementation: server.js spawns a local 'uvx blender-mcp' process and proxies JSON-RPC tool calls such as execute_code, get_scene_info, and download/search helpers. There are no unrelated environment variables, credentials, or config paths requested.
ℹ
Instruction Scope
SKILL.md instructs the agent to use tools that download assets and to run arbitrary BPY (Blender Python) via execute_code. This is expected for a remote-control bridge, but execute_code grants the ability to run arbitrary Python inside Blender (file operations, external requests if allowed by Blender environment). The instructions also expect reading/using local scripts/ and writing .blend files in the working directory — consistent with the skill but worth noting as a privileged action within the Blender environment.
✓
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded or extracted by the platform. Code files are included in the package, and server.js uses child_process.spawn to launch a local binary. No remote download URLs or archive extraction are present in the install metadata.
✓
Credentials
The skill declares no required environment variables or credentials. The code reads process.env.USERPROFILE (to check for a local uvx.exe path) which is proportional to locating the local helper binary. No secrets or unrelated tokens are requested.
✓
Persistence & Privilege
The skill does not set always:true, does not attempt to modify other skills or agent-wide configs, and only spawns a local helper process. Autonomous invocation remains possible (platform default) but is not combined with elevated persistence or cross-skill access.
Assessment
This skill appears to be what it claims: a bridge to a local blender-mcp helper. Before installing, confirm you trust the 'uvx' / 'blender-mcp' binary that will be executed (the bridge launches that local binary via child_process). Be aware that the tool exposes execute_code which runs arbitrary Blender Python (BPY) — that can read/write files, run network requests if Blender allows them, or run any script in your scripts/ directory. To reduce risk: only use this skill with a trusted uvx/blender-mcp binary, run Blender in an isolated environment if possible, review any helper scripts in scripts/ and the BPY code being executed, and avoid providing it access to sensitive directories. If you don't plan to use execute_code or external asset downloads, consider removing or sandboxing those capabilities.
✗
server.js:29
Shell command execution detected (child_process).
✗
test.js:5
Shell command execution detected (child_process).
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.

Like a lobster shell, security has layers — review code before you run it.

latestvk972hdbacpmsn7ytvzvy6g1ptd82zmez

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments