Works with the AI Agents you already use
crg cvss4 scorer
Generate justified CVSS v4.0 Base scores and vectors using audited lookup tables for technical vulnerabilities.
$10
crg cvss4 scorer
Example session with this skill installed
Score this: An unauthenticated attacker on the network can exploit a buffer overflow in the web server to gain full control of the host. No other systems are reachable from this server.
- Read your context and instructions
- Compiled the crg cvss4 scorer
The vulnerability has been analyzed as a Critical severity flaw. The score was retrieved from the CVSS v4.0 lookup tables based on the identified Base metrics.
1. Vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
2. Metrics and justification
| Metric | Value | Justification |
|---|---|---|
| AV | N | Attacker reaches the web server over the network. |
| AC | L | No specific configuration or complex conditions required for exploit. |
| AT | N | No specific network topologies or temporal states needed. |
| PR | N | No login or specialized privileges required to reach the buffer overflow. |
| UI | N | Exploitation occurs without any user interaction. |
| VC | H | Full loss of confidentiality as attacker gains host control. |
| VI | H | Full loss of integrity as attacker gains host control. |
| VA | H | Full loss of availability as attacker gains host control. |
| SC | N | User stated no other systems are affected/reachable. |
| SI | N | No impact to subsequent systems. |
| SA | N | No availability impact to subsequent systems. |
3. Score and lookup trace
Score: 9.3
Lookup trace: file references/cvss4/AV-N_AC-L_AT-N_PR-N_UI-N.md; line VC:H VI:H VA:H; entry NNN=9.3
4. Severity
Critical (9.0–10.0)
5. What would change the score
| Uncertain metric | Alternative | New score (lookup trace) |
|---|---|---|
| PR | L | 8.7 (file AV-N_AC-L_AT-N_PR-L_UI-N.md, line VC:H VI:H VA:H, entry NNN=8.7) |
6. Caveat
CVSS rates the technical severity of a vulnerability, not organizational risk.
Next steps
- Verify if any network-level authentication (PR:L) is actually required in your specific environment.
- Confirm if the server is truly isolated (SC/SI/SA:N) or if it has access to internal management VLANs.
- Use this score to inform your internal patching priority and risk assessment.
Connects securely to your tools. The creator never sees your data.
About this skill
Estimating vulnerability severity by hand is prone to calculation errors and subjective bias. This skill automates CVSS v4.0 Base scoring by mapping technical descriptions to precise vectors and retrieving scores from verified lookup tables. It eliminates the risks of manual computation and memory-based estimation.
What it does
- Standardized scoring generates CVSS v4.0 Base vectors from technical vulnerability descriptions or CVE IDs.
- Table-based lookup retrieves exact scores from bundled reference files rather than calculating them.
- Metric justification provides a per-metric table explaining values based on user-provided evidence or identified gaps.
- Sensitivity analysis identifies uncertain metrics and reports how alternative values would shift the final score.
- Applicability screening filters out non-technical risks like poor governance or fraud where CVSS is inappropriate.
How it works
- Intake analyzes the vulnerability description, requesting more detail if the attack vector or impact is unclear.
- Metric Selection assigns values for the 11 Base metrics (AV, AC, AT, PR, UI, VC, VI, VA, SC, SI, SA).
- Lookup opens the specific reference Markdown file and line corresponding to the vector to extract the score.
- Validation flags assumptions as analytical estimates or information gaps requiring organizational review.
Frameworks & tools
This skill uses the CyberRiskGuardian method and the FIRST CVSS v4.0 specification. It relies on a local filesystem-based lookup index for score retrieval.
Why this beats prompting it yourself
Generic LLM prompts often hallucinate CVSS scores or use outdated v3.1 logic. This skill enforces the v4.0 spec and mandates a file-based lookup trace, ensuring every decimal point is grounded in the official tables.
Use cases
- Security Triage quickly determining the technical severity of a new bug bounty report or CVE.
- Audit Verification checking if a vendor-supplied CVSS v4.0 score matches the actual specification tables.
- Report Generation creating justified scoring sections for penetration testing or vulnerability assessment reports.
Known limitations
Limited to CVSS v4.0 Base metrics only. It does not support Threat, Environmental, or Supplemental groups, nor does it score non-technical risks like policy gaps.
Only scores CVSS v4.0 Base metrics. No support for v2 or v3.x. Requires technical descriptions of flaws; cannot score organizational or governance risks.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 7 days ago