SkillSpector: NVIDIA's Security Scanner for AI Agent Skills

Introduction

AI agent skills, utilized by platforms such as Claude Code, Codex CLI, and Gemini CLI, often execute with implicit trust and minimal vetting. Research indicates a significant number of these skills contain vulnerabilities, with a notable percentage showing likely malicious intent. SkillSpector addresses this critical concern by providing a robust security scanner that helps answer the fundamental question: "Is this skill safe to install?"

Developed by NVIDIA, SkillSpector is an integral part of the NVIDIA Verified Skills pipeline, which meticulously scans, evaluates, and signs agent skills prior to their publication. Skills that successfully pass these rigorous checks are then made available in the NVIDIA skills catalog.

Why Use SkillSpector & Key Features

The proliferation of AI agent skills necessitates a strong security posture. SkillSpector is designed to proactively detect a wide array of threats, safeguarding your AI agents from compromise. Here are its key features:

• Multi-format Input: Scan various sources including Git repositories, URLs, zip files, local directories, or single files.
• Extensive Vulnerability Patterns: Detects 71 vulnerability patterns across 17 categories, covering prompt injection, data exfiltration, privilege escalation, supply chain risks, excessive agency, output handling, system prompt leakage, memory poisoning, tool misuse, rogue agent, anti-refusal, trigger abuse, dangerous code (AST), taint tracking, YARA signatures, MCP least privilege, and MCP tool poisoning.
• Two-Stage Analysis: Employs a fast static analysis for broad detection, complemented by an optional LLM semantic evaluation to refine findings and reduce false positives.
• Live Vulnerability Lookups: Integrates with OSV.dev to provide real-time CVE data for dependencies, with an automatic offline fallback.
• Multiple Output Formats: Generates reports in various formats, including Terminal, JSON, Markdown, and SARIF, for diverse integration needs.
• Risk Scoring: Provides a clear 0-100 risk score with severity labels and actionable recommendations, helping you quickly assess the threat level.
• Baseline / False-Positive Suppression: Allows you to accept known findings via glob-rules or fingerprint baselines, ensuring that subsequent scans highlight only new issues.

Installation

SkillSpector offers flexible installation options to suit your workflow.

Quick Install with uv (CLI-only)

uv tool install git+https://github.com/NVIDIA/skillspector.git
# Update later: uv tool update skillspector

# If you plan to run 'skillspector mcp', install the MCP extra:
uv tool install 'skillspector[mcp] @ git+https://github.com/NVIDIA/skillspector.git'

From Source

# Clone the repository
git clone https://github.com/NVIDIA/skillspector.git
cd skillspector

# Create and activate virtual environment
uv venv .venv && source .venv/bin/activate
# or: python3 -m venv .venv && source .venv/bin/activate

# Install for production use
make install

# Or install with development dependencies
make install-dev

Docker (no Python required)

# Build the image
make docker-build
# or: docker build -t skillspector .

# Scan a local directory
docker run --rm -v "$PWD:/scan" skillspector scan ./my-skill/ --no-llm

# Scan with LLM analysis (using a .env file for credentials)
cat > .env <<'EOF'
SKILLSPECTOR_PROVIDER=anthropic
ANTHROPIC_API_KEY=sk-ant-...
EOF
docker run --rm \
  -v "$PWD:/scan" \
  --env-file .env \
  skillspector scan ./my-skill/

Examples

Basic Usage

# Scan a local skill directory
skillspector scan ./my-skill/

# Scan a single SKILL.md file
skillspector scan ./SKILL.md

# Scan a Git repository
skillspector scan https://github.com/user/my-skill

# Scan a zip file
skillspector scan ./my-skill.zip

Output Formats

# Terminal output (default)
skillspector scan ./my-skill/

# JSON output for machine readability
skillspector scan ./my-skill/ --format json --output report.json

# Markdown output for documentation
skillspector scan ./my-skill/ --format markdown --output report.md

# SARIF output for CI/CD integration
skillspector scan ./my-skill/ --format sarif --output report.sarif

LLM Analysis Configuration

For enhanced semantic analysis, SkillSpector can integrate with various LLM providers. For example, using OpenAI:

export SKILLSPECTOR_PROVIDER=openai
export OPENAI_API_KEY=sk-...
skillspector scan ./my-skill/

Or to skip LLM analysis for faster, static-only scans:

skillspector scan ./my-skill/ --no-llm

Links

• GitHub Repository: NVIDIA/SkillSpector
• Official Documentation: Scan agent skills before installation
• License: Apache License 2.0