Skills/Glama/design-os-3d-blender

design-os-3d-blender@0.2.0

VERIFIED· install only

Publisher claims: "Enables AI agents to generate dimensionally accurate mechanical parts (gears, enclosures, brackets, assemblies) in headless Blender from plain-English specs or JSON parameters, then verify them against manifold, bounding-box and print-production gates and export glTF/STL assets. It also scaffolds interactive Three.js CAD viewer pages with orbit controls, wireframe toggles and exploded-view scrubbing." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher jangtrinh · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add design-os-3d-blender
WatchReport an issue

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: Verified 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.

$vet-skills run --net declared -- <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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 81/100 (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 · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/knowledge-catalog.py:67 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filepaths.update(p for p in ('.project-agent.md', 'AGENTS.md', 'CLAUDE.md') if (root / p).is_file())Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload action.claude/skills/img2threejs/SKILL.md:163 · File type combined with upload action — agent may exfiltrate local data files…scores + decision): `forge/stage4_review/append_review.py object-sculpt-spec.json --pass-id <pass> --fidelity <0-1> --action <continue|refine-spec|refine-code|request-input|stop> --summary "..." --render-screenshot <shot> --comparison-imag…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/native_pipeline/runner.py:242 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload action.agents/skills/blender-agent-core/SKILL.md:39 · File type combined with upload action — agent may exfiltrate local data files1. **Contract first** — purpose first (render-only / print / both, default `both`), then spec.json for a production part; fidelity contract for a reference; missing numbers → `request-input`.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/run-qremeshify.py:40 · Python subprocess execution detectedresult = 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/production-gate.py:96 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, timeout=args.timeout, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload action.agents/skills/img2threejs/SKILL.md:163 · File type combined with upload action — agent may exfiltrate local data files…scores + decision): `forge/stage4_review/append_review.py object-sculpt-spec.json --pass-id <pass> --fidelity <0-1> --action <continue|refine-spec|refine-code|request-input|stop> --summary "..." --render-screenshot <shot> --comparison-imag…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/run-qremeshify.py:64 · Python subprocess execution detectedprocess = subprocess.Popen(command, env=environment, start_new_session=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/hq-coverage-gate.py:31 · Python subprocess execution detectedchild = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True, bufsize=1)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload action.claude/skills/blender-agent-core/SKILL.md:39 · File type combined with upload action — agent may exfiltrate local data files1. **Contract first** — purpose first (render-only / print / both, default `both`), then spec.json for a production part; fidelity contract for a reference; missing numbers → `request-input`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Collapsed <details> block carrying instructionsREADME.md:138 · Collapsed <details> block carrying instructions<summary>Verify or uninstall</summary> **Verify installation:** ```bash python3 scripts/self_check.py ``` Or run `/doctor` inside Claude Code / Codex to inspectFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈28,427 tok
9 files · 80 in bundle

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.