Caveat verdict

box2robot

box2robot-skills

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Box2Robot controls physical robotic arms via HTTP calls to the declared robot.box2ai.com endpoint; the skill explicitly documents safety requirements, human supervision requirements, and that all network calls go exclusively to B2R_SERVER — transparent and legitimate use of its capabilities.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

33
security
80
transparency
90
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILLS.md · code · TOKEN="<jwt_token>

Pattern match medium

subprocess execution — runs system commands from Python

b2r.py · prose · downgraded · subprocess.run(

Pattern match low

Opens WebSocket connection

b2r.py · prose · downgraded · WebSocket

Pattern match low

Python os.environ.get — reads environment variable

b2r.py · prose · downgraded · os.environ.get(

Pattern match low

Python aiohttp session — async network access

b2r.py · prose · downgraded · aiohttp.ClientSession

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outpackage_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API