Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →CISA Known Exploited Vulnerabilities (KEV) catalog. List actively exploited vulnerabilities prioritized by CISA. **Dependency**: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
.claude/skills/x-cmd-x-kev/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -70% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -68% | 0% |
> CISA KEV Catalog - Known Exploited Vulnerabilities listing.
bash# List all KEV vulnerabilities x kev ls # List top 100 KEVs x kev top 100
| Command | Description | |---------|-------------| | x kev ls | List all vulnerabilities in KEV catalog | | x kev top [n] | List top N vulnerabilities |
bash# List all KEV vulnerabilities x kev ls # Get top 50 x kev top 50 # Get top 100 x kev top 100
The CISA Known Exploited Vulnerabilities (KEV) catalog contains vulnerabilities that:
Reference: CISA KEV Catalog
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,261 | 2,442 | -80% | 1 | 1 | 0% | 2,113 | 662 | -69% | 0 | 0 | — |
case-02 | fail→pass | 7,716 | 9,907 | +28% | 1 | 1 | 0% | 1,200 | 675 | -44% | 0 | 0 | — |
case-03 | fail→pass | 11,532 | 9,461 | -18% | 1 | 1 | 0% | 1,980 | 602 | -70% | 0 | 0 | — |
case-04 | fail→pass | 17,839 | 2,341 | -87% | 1 | 1 | 0% | 1,201 | 671 | -44% | 0 | 0 | — |
case-05 | fail→pass | 11,343 | 2,780 | -75% | 1 | 1 | 0% | 2,004 | 641 | -68% | 0 | 0 | — |
case-06 | fail→pass | 13,805 | 4,082 | -70% | 1 | 1 | 0% | 2,453 | 652 | -73% | 0 | 0 | — |
case-07 | fail→pass | 14,429 | 2,190 | -85% | 1 | 1 | 0% | 2,138 | 606 | -72% | 0 | 0 | — |
case-08 | fail→pass | 14,387 | 2,586 | -82% | 1 | 1 | 0% | 2,420 | 691 | -71% | 0 | 0 | — |
case-09 | fail→pass | 4,960 | 4,717 | -5% | 1 | 1 | 0% | 716 | 721 | +1% | 0 | 0 | — |
case-10 | fail→pass | 7,872 | 7,718 | -2% | 1 | 1 | 0% | 1,138 | 830 | -27% | 0 | 0 | — |
case-11 | fail→pass | 9,028 | 7,277 | -19% | 1 | 1 | 0% | 1,278 | 731 | -43% | 0 | 0 | — |
case-12 | fail→pass | 10,890 | 6,120 | -44% | 1 | 1 | 0% | 1,592 | 659 | -59% | 0 | 0 | — |
case-13 | fail→pass | 13,114 | 5,619 | -57% | 1 | 1 | 0% | 2,560 | 606 | -76% | 0 | 0 | — |
case-14 | pass→pass | 6,626 | 4,231 | -36% | 1 | 1 | 0% | 548 | 740 | +35% | 0 | 0 | — |
case-15 | pass→pass | 7,594 | 3,442 | -55% | 1 | 1 | 0% | 1,000 | 793 | -21% | 0 | 0 | — |
case-16 | fail→pass | 6,580 | 8,650 | +31% | 1 | 1 | 0% | 1,030 | 715 | -31% | 0 | 0 | — |
case-17 | fail→pass | 18,038 | 2,578 | -86% | 1 | 1 | 0% | 2,206 | 673 | -69% | 0 | 0 | — |
case-18 | pass→pass | 12,624 | 2,426 | -81% | 1 | 1 | 0% | 1,150 | 630 | -45% | 0 | 0 | — |
case-19 | fail→pass | 10,862 | 2,478 | -77% | 1 | 1 | 0% | 1,749 | 667 | -62% | 0 | 0 | — |
case-20 | pass→pass | 8,486 | 9,529 | +12% | 1 | 1 | 0% | 1,442 | 1,746 | +21% | 0 | 0 | — |
case-21 | pass→pass | 11,674 | 10,526 | -10% | 1 | 1 | 0% | 1,763 | 1,532 | -13% | 0 | 0 | — |
case-22 | pass→pass | 11,456 | 6,621 | -42% | 1 | 1 | 0% | 1,945 | 1,631 | -16% | 0 | 0 | — |
case-23 | pass→pass | 14,532 | 7,045 | -52% | 1 | 1 | 0% | 2,215 | 1,432 | -35% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +70 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.