Install any skill in seconds. Free to start, no credit card required.
Get Started Free →The Common Vulnerability Scoring System (CVSS) is the industry standard framework maintained by FIRST (Forum of Incident Response and Security Teams) for assessing vulnerability severity. CVSS v4.0 (r
.claude/skills/prioritizing-vulnerabilities-with-cvss-scoring/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-21 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-15 | ✗→✓ | ▲ Improved | — | — |
The Common Vulnerability Scoring System (CVSS) is the industry standard framework maintained by FIRST (Forum of Incident Response and Security Teams) for assessing vulnerability severity. CVSS v4.0 (released November 2023) introduces refined metrics for more accurate scoring. This skill covers calculating CVSS scores, interpreting vector strings, and using CVSS alongside contextual factors like EPSS and CISA KEV for effective vulnerability prioritization.
Represent the inherent characteristics of a vulnerability:
Exploitability Metrics:
Impact Metrics (Vulnerable System):
Impact Metrics (Subsequent System):
Modified versions of base metrics reflecting local deployment context, plus:
| Score Range | Severity | |-------------|----------| | 0.0 | None | | 0.1 - 3.9 | Low | | 4.0 - 6.9 | Medium | | 7.0 - 8.9 | High | | 9.0 - 10.0 | Critical |
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NThis example represents a network-exploitable vulnerability requiring no privileges, no user interaction, no attack requirements, with high impact on confidentiality, integrity, and availability of the vulnerable system.
For each vulnerability, evaluate:
Example: CVE-2024-3094 (XZ Utils Backdoor)
Attack Vector: Network (N) - Exploitable over network
Attack Complexity: High (H) - Specific conditions required
Attack Requirements: Present (P) - Specific build/config needed
Privileges Required: None (N) - No authentication needed
User Interaction: None (N) - No victim action needed
Vulnerable System Impact:
Confidentiality: High (H) - Complete access to SSH keys
Integrity: High (H) - Arbitrary code execution
Availability: High (H) - Full system compromise
Subsequent System Impact:
Confidentiality: High (H) - Lateral movement possible
Integrity: High (H) - Network-wide compromise
Availability: None (N) - No downstream availability impact
Vector: CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:NEnrich CVSS with real-world threat data:
Exploit Maturity: Attacked (A) - Active exploitation in the wild
EPSS Score: 0.94 - 94% probability of exploitation in 30 days
CISA KEV: Listed - Mandatory remediation for federal agenciesAdjust for organizational context:
Confidentiality Req: High (H) - Handles PII/financial data
Integrity Req: High (H) - Critical business process
Availability Req: Medium (M) - Has DR/failover capability
Modified Attack Vector: Network (N) - Internet-facing deploymentCombine CVSS with additional prioritization factors:
| Factor | Weight | Source | |--------|--------|--------| | CVSS Base Score | 25% | NVD/Scanner | | EPSS Score | 25% | FIRST EPSS API | | Asset Criticality | 20% | Asset inventory/CMDB | | CISA KEV Listed | 15% | CISA catalog | | Network Exposure | 15% | Network segmentation data |
| Priority Level | CVSS Range | EPSS | Asset Tier | SLA | |---------------|------------|------|------------|-----| | P1 - Emergency | 9.0-10.0 | >0.5 | Tier 1 | 24-48 hours | | P2 - Critical | 7.0-8.9 | >0.3 | Tier 1-2 | 7 days | | P3 - High | 7.0-8.9 | <0.3 | Tier 2-3 | 14 days | | P4 - Medium | 4.0-6.9 | Any | Any | 30 days | | P5 - Low | 0.1-3.9 | Any | Any | 90 days |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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. 22 cases were attempted. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.