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.
Why this job: says: security scanner, prompt injection; topics: agent-security, security-tools, ai-security, prompt-injection
What it does
- 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, tri
- 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
Get started
uv tool install git+https://github.com/NVIDIA/skillspector.git
# Update later: uv tool update skillspector - Maintenance
- Active
- Last commit 3 days ago
- Stars
- 24,955
- +898 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v2.13.4
- Released 5 days ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 79% closed
- 79 still open
- Pull requests
- 511 merged
- 100 waiting
- Releases
- 22
- 22 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| hashgraph-online / hol-guard | 1,080 | today | Apache-2.0 | Mac, Linux |
| asamassekou10 / ship-safe | 871 | 23 days ago | MIT | No downloads |
| uber / ADR | 2,128 | 24 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- TypeScript 1%
- JavaScript <1%
- YARA <1%
Topics
- agent-security
- agent-skills
- agentic-ai
- ai-security
- claude-code
- mcp
- prompt-injection
- security-scanner
- security-tools
- security-workflow
- supply-chain-security
Project record
- JobAI security
- StatusFeatured
- Commits2,088
- Forks2,191
- Watching88
- Stars in 28 days+2,663
- CreatedMar 21, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026