NVIDIA/SkillSpector · freshness 100/100 · rescored August 14, 2026
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.
The answer
Yes. SkillSpector is actively maintained — last commit today, freshness 100/100.
| Signal | Value | Effect | Why |
|---|---|---|---|
| Last commit | today | none | Pushed today. |
| Commits, 90 days | 100+ | none | 100+ commits in the last 12 weeks. |
| Last release | v2.9.4 · today | +4 | Released v2.9.4 0 days ago; 10 releases in the last year. |
| Release cadence | 1 days, median | not scored | |
| Issue response | too few issues to sample | none | Not enough recent issues to measure a response time. |
| Unanswered issues | 100% of 4 sampled | not scored | |
| Committers, 90 days | 21 | +5 | 21 people committed in the last 90 days. |
| Bus factor | 3 | not scored | |
| Archived | no | not scored | |
| Licence | Apache-2.0 | not scored | |
| Stars | 14,609 | not scored | |
| Open issues | 45 | not scored |
The same verdict, in words
Against it: The signals totalled 109; 100 is the ceiling. For it: Released v2.9.4 0 days ago; 10 releases in the last year. 21 people committed in the last 90 days.
Last push today, 100+ commits in the last 90 days, last release v2.9.4 today, 21 committers in 90 days. Read from the GitHub API; NVIDIA/SkillSpector carries 14,609 stars and 45 open issues.
The rest of spec frameworks
8 tools shown| Tool | Category | Status | Freshness | Last commit | Stars |
|---|---|---|---|---|---|
| get-shit-donegsd-build/get-shit-doneis get-shit-done maintained? | Spec frameworks | Archived | 0 | 2mo | 65k |
| AI Dev Taskssnarktank/ai-dev-tasksis AI Dev Tasks maintained? | Spec frameworks | Dead | 22 | 9mo | 7.8k |
| Task Mastereyaltoledano/claude-task-masteris Task Master maintained? | Spec frameworks | Slowing | 29 | 4mo | 28k |
| Claude-Code-Game-StudiosDonchitos/Claude-Code-Game-Studiosis Claude-Code-Game-Studios maintained? | Spec frameworks | Slowing | 52 | 3mo | 24k |
| ccpmautomazeio/ccpmis ccpm maintained? | Spec frameworks | Slowing | 47 | 5mo | 8.3k |
| Infinite Agentic Loopdisler/infinite-agentic-loopis Infinite Agentic Loop maintained? | Spec frameworks | Slowing | 39 | 5mo | 609 |
| Superpowersobra/superpowersis Superpowers maintained? | Spec frameworks | Maintained | 100 | 1d | 272k |
| ECCaffaan-m/ECCis ECC maintained? | Spec frameworks | Maintained | 100 | 0d | 240k |
Put this measurement in your README
A badge carrying this verdict and the freshness behind it, recomputed nightly from the GitHub API. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://stillshipping.kynth.studio/tool/skillspector)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.
