skill-inspector

skill-inspector is a skill in NVIDIA/SkillSpector, last changed 8 Oct 2026. It can run shell commands. Our pattern check flagged nothing at commit e717246 on 27 Oct 2026.

Pattern check: nothing flagged · commit e717246 · 27 Oct 2026

Install
From the author
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
Licence
Apache 2.0
Repo stars
22.8k
Publisher
NVIDIA
Files
1 file
Checked
e717246 (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit e717246, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit e717246, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/SkillSpector.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin e7172462caf367736645f66c1aa154ca5f9c64dc &&
  git -C "$tmp" sparse-checkout set -- skills/skill-inspector &&
  git -C "$tmp" checkout -q e7172462caf367736645f66c1aa154ca5f9c64dc &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/skill-inspector &&
  cp -R "$tmp"/skills/skill-inspector/. .claude/skills/skill-inspector/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit e717246. This is how much a skill can do, not whether it is risky.

What it can touch: Scripts or outside hosts

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

Pattern check

Pattern check: nothing flagged · commit e717246 · 27 Oct 2026

We checked every text file in this skill, at commit e717246 on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Claude CodePasses
  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      The description is 228 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

1 file

PathSize
SKILL.md (opens in a new tab)7.4 KB