---
slug: "skillspector"
name: "SkillSpector"
effect: "Scans agent skills for prompt injection, data exfiltration and supply-chain risks before you install them"
category: "devtool"
tier: "rising"
url: "https://docs.nvidia.com/skills/scanning-agent-skills"
github: "NVIDIA/SkillSpector"
pricing: "open-source"
license: "Apache-2.0"
tags: ["security", "skills", "scanner", "mcp", "sarif", "prompt-injection"]
platforms: ["claude-code", "codex", "gemini-cli", "docker"]
install_kind: "cli"
date_added: "2026-10-15"
rank: 10
rising_score: 52
stars: 20224
star_velocity: 97.1
velocity_basis: "since creation"
created_at: "2026-03-21T00:28:43Z"
pushed_at: "2026-10-14T18:48:16Z"
signals_status: "ok"
signals_fetched_at: "2026-10-15T05:02:34.711Z"
page: "https://agenttooldrop.com/tools/skillspector"
---

# SkillSpector

Scans agent skills for prompt injection, data exfiltration and supply-chain risks before you install them

Category: Devtools. Tier: new and rising, rank 10 by new and rising score (52 of 100). Pricing: Open source. License: Apache-2.0.

Platforms: claude-code, codex, gemini-cli, docker.

## Why you would want it

SkillSpector scans a skill from a Git repo, URL, zip file, directory or single SKILL.md against 71 patterns in 17 categories, including prompt injection, data exfiltration, privilege escalation, MCP tool poisoning and MCP least privilege. It runs static analysis first and an optional LLM evaluation second, gives a 0 to 100 risk score, and writes terminal, JSON, Markdown or SARIF reports. It can also run as an MCP server with a scan_skill tool, so Claude Code, Codex CLI or Gemini CLI can gate skill and MCP installs on the result. It is part of NVIDIA's Verified Skills pipeline.

## Best for

- Vetting third-party skills before install
- CI checks with SARIF output
- Gating installs from inside an agent

## Use it when

You install skills or MCP servers from public repositories and want a report on risky patterns before they reach your agent.

## Skip it if

You only use skills you wrote yourself. The optional LLM analysis sends skill content to the configured provider with your API key; --no-llm runs static checks only. The README notes the stdio MCP transport still has an initialize hang reported in issue #199.

## Editor note

The MCP server needs the mcp extra: uv tool install 'skillspector[mcp] @ git+https://github.com/NVIDIA/skillspector.git', then skillspector mcp.

## Install

Install with uv:

```sh
uv tool install git+https://github.com/NVIDIA/skillspector.git
```

Source: https://github.com/NVIDIA/SkillSpector#installation

## Live signals

Fetched 2026-10-15T05:02:34.711Z (status: ok).

- Repository: NVIDIA/SkillSpector
- Repository created: 2026-03-21
- Stars: 20,224 (GitHub's count; it cannot be authenticated)
- Stars per day, since repo creation: 97.1 (an average over the repo's life, not a growth rate)
- Forks: 1,776
- Open issues and PRs: 141
- License (GitHub): Apache-2.0
- Last push: 2026-10-14
- Latest release: v2.12.0 (2026-09-23)

## Links

- Website: https://docs.nvidia.com/skills/scanning-agent-skills
- GitHub: https://github.com/NVIDIA/SkillSpector
- Install instructions verified at: https://github.com/NVIDIA/SkillSpector#installation
- Source for this entry: https://github.com/NVIDIA/SkillSpector#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/skillspector
- Full catalog (JSON): https://agenttooldrop.com/tools.json