NVIDIA /SkillSpector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
★ 26,197⑂ 2,323👁 95⑃ 709● 404▤ 22
+173
日增长
+2,011
周增长
+6,337
月增长
26,197
stars
2,323
forks
95
watchers
709
prs
404
issues
22
releases
README
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills (used by Claude Code, Codex CLI, Gemini CLI, etc.) execute with implicit trust and minimal vetting. In the 31,132-skill analyzed subset of the research dataset, 26.1% of skills contain vulnerabilities and 5.2% show likely malicious intent. SkillSpector helps you answer: "Is this skill safe to install?" SkillSpector is part of the NVIDIA Verified Skills pipeline, which scans, evaluates, and signs agent skills before publication. Skills that pass are published to the NVIDIA skills catalog. Documentation - Scan agent skills before installation — Hosted guide: when to scan, how to read a report, and how to gate installs. - Development guide — Architecture, package layout, and how to extend the analyzer pipeline. - Security policy — Report suspected vulnerabilities privately to NVIDIA PSIRT. - Analysis resource bounds — Fail-closed bundle, parser, nested-artifact, ledger, and finding ceilings. - Pi extension — Install SkillSpector as a Pi tool for scanning skills from inside agent sessions. - OpenCode extension — Install SkillSpector as an OpenCode tool and /skillspector command for scanning skills from inside agent sessions. Features - Multi-format input: Scan Git repos, URLs, zip files, directories, or single files - 71 vulnerability patterns across 17 categories: prompt injection, data exfiltration, privilege escalation, supply chain, 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: Fast static analysis + optional LLM semantic evaluation - Live vulnerability lookups: SC4 queries OSV.dev for real-time CVE data with automatic offline fallback - Multiple output formats: Terminal, JSON, Markdown, and SARIF reports - Risk scoring: 0-100 score with severity labels and clear recommendations - Baseline / false-positive suppression: Accept known findings via a glob-rule or fingerprint baseline so re-scans surface only new issues (docs) Quick Start Installation Open-source software notice: This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use. Create and activate a virtual environment first (all make targets assume the venv is active). Use uv or pip; the Makefile uses uv if available, otherwise pip. Quick install with uv (CLI-only): bash 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 at install time: bash uv tool install 'skillspector[mcp] @ git+https://github.com/NVIDIA/skillspector.git' From source: bash Clone the repository git clone https
Top issues
#596AE1 classifies opaque-by-type assets as `analysis-evasion` HIGH, discarding the ledger `reason_code` that distinguishes them from real coverage failures8 comments · 2026-09-20#694static_parse_limit on valid Rust, Python and POSIX shell source leaves files partially inspected7 comments · 2026-09-30#37Creates false positives on pure text-based content7 comments · 2026-06-13#644Static-pattern false positives found scanning public skills (P2 BOM, RA2 plist, EA3 OFL, plus design-level items)6 comments · 2026-09-26#456Add opt-in compact prompts mode to reduce LLM token usage6 comments · 2026-08-28#271Publish SkillSpector to PyPI for easier installation and integration6 comments · 2026-07-13#121Feature: MCP server registry scanning — complementary to skill scanning6 comments · 2026-06-20#363Oversized companion file causes SkillSpector to skip analysis of unrelated skill files (v2.8.2) (another malicious skill example that bypasses this scanner)5 comments · 2026-08-12
Discussions
#920skillspector-rs: an optimized Rust port of the static analysis (no LLM yet)0 comments · 2026-10-27#871Clarification requested: v2.13.0 release version verification0 comments · 2026-10-18#651Missing category and findings when usellm is set0 comments · 2026-09-28#549SkillSpector-TKV: A lightweight (~144KB) native port in TokenVector with GUI, offline-first scan, and parity rules0 comments · 2026-09-15
Latest release
SkillSpector v2.13.4 v2.13.4 2026-11-04SkillSpector 2.13.4 This maintenance release includes the v2.13.3 fixes and selected improvements to provider compatibility, source inspection, and recovery of malformed AI responses. Fixes - 806: provider compatibility and structured responses for GPT-6.1 Sol and Claude Opus 5.5 across supported routes. - 947, 950, and 973: bounded parsing of shell, PowerShell, JavaScript templates, Python strings, and Markdown documentation. - 974: inspect supported generated shell helpers and archived sources without executing uploaded code. Dependencies outside the uploaded skill and unprov
相关报道 (5)
News & coverage (13)
Hacker NewsSkillSpector▲ 49 · 4 comments · 2026-06-12vc.ruСкилл с GitHub может оказаться с сюрпризом2026-10-28noteNVIDIA releases agent skill inspection tool. While AI budgets are increasing, only 29% of large companies can track spending across the entire organization | amu_lab AI/DX News ...2026-10-26noteHow to use SkillSpector: NVIDIA's free OSS for inspecting AI skills before installation, and how to read the scores2026-10-14Help Net SecurityHottest cybersecurity open-source tools of the month: August 20262026-08-25marktechpostBuilding an Advanced AI Skill Security Auditing Pipeline with NVIDIA SkillSpector, LangGraph, YARA Rules, SARIF, and CI Policy Gates2026-08-04Help Net SecuritySkillSpector: NVIDIA’s open-source security scanner for AI agent skills2026-08-02noteWhat is NVIDIA SkillSpector? How to Safely Verify Local AI Agent Skills [Introduction Guide]2026-06-21marktechpostNVIDIA SkillSpector Guide: Scanning AI Skills for Security Risks with Static Analysis and SARIF Reports2026-06-16xHow NVIDIA's SkillSpector works and How to add It to your skill PRs2026-06-06