Skills/ClawHub/nvidia-kimi-vision

nvidia-kimi-vision@1.0.3

CAUTION· static only

Publisher claims: "Analyze images using NVIDIA Kimi K2.5 vision model via NVIDIA NIM API. Perfect for adding vision to non-vision models like MiniMax M2.5, GLM-5, or any model..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher miladnoo · publishing for 276 daysInstalls 2,413Last detonated 24 min ago

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.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-21 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag. 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

CRITICAL
Fake instruction boundary tagSKILL.md:61 · Fake instruction boundary tagpython3 scripts/analyze_image.py <image_path> "<prompt>" [api_key]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 254 lines in 3 files.

Cost to the agent

Instructions loaded
≈620 tok
1 file · 3 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.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim miladnoo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim miladnooPropose a patch to the maintainer