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.
About the project
Security scanner for AI agent skills: detects vulnerabilities, malicious patterns, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before installation.
Useful for
- Scan a downloaded Claude Code skill for prompt injection and data exfiltration before installing it
- Run the scanner over an MCP skills repository and produce a SARIF report for CI
- Set up a baseline so re-scans surface only new findings
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 81 stars so far today, about 99 expected by the end of the day.
- GitHub Trending Python today: #5, +157 stars.
- About 22 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 17,750
- Stars in a day
- 99
- Forks
- 1,522
- Issues and pull requests
- 574
- Watchers
- 71
- Language
- Python
- License
- Apache-2.0
- Latest release
- v2.11.2 · September 9, 2026
- Created
- March 21, 2026
- Last push
- September 18, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 18, 2026GitHub Trending Python today: #5, +157 stars
Similar projects
-
9.7
cloudflare/security-audit-skill
A coding-agent skill that turns the agent into a security auditor, running a multi-phase code audit with independently verified, machine-readable findings.
-
6.6
yynxxxxx/gpt_sub_analysis
A guide to analyzing the ChatGPT iOS subscription flow: it describes intercepting the buyProduct request via Reqable and SSL Kill Switch 3 and rewriting the offerName and salableAdamId fields to obtain the Pro 20x…
-
5.8
ctdal/cve-2026-41940-PoC
PoC exploit for CVE-2026-41940, a critical authentication bypass in cPanel & WHM (CVSS 10.0) that grants unauthenticated root-level WHM access by injecting CRLF sequences into server-side session files.
-
5.3
BennyThink/NFCX
Cross-platform GUI desktop app for NFC card work: reader discovery, MIFARE Classic reads, dumps, key management, and key recovery. For cards you own or are authorized to test.
-
4.9
NationalSecurityAgency/ghidra
A software reverse engineering framework from the NSA: disassembly, decompilation, graphing and scripting for analyzing compiled code on Windows, macOS and Linux.
-
4.6
shinthink/blitzstrike
A TypeScript/Bun MCP server packaging a pentest methodology into three tiers: attack-surface reconnaissance, source-to-sink tracing, and live validation of findings before reporting.