Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Calibrate final risk scores for findings v1.0.0

Use this resource to assign a final risk score to confirmed security findings

New

  • 598 downloads
  • 104 likes
  • 217 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install final-risk-score-calibration

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent loads the processed findings, applies a risk matrix based on reproduction evidence, production viability and the threat model, then appends the score to each finding file. You get a prioritized ranking.

Mostly picked by

Updated November 2, 2026

Card for the “Calibrate final risk scores for findings” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: role, command and input-output rules
  • references/calibration_rules.md: risk calibration rules

Good fit for

  • Confirmed findings need to be ranked by severity
  • You want a justified risk score before prioritizing fixes

Not for

    Tags

    • security
    • risk
    • score
    • prioritization

    About

    You say

    “Calibrate the risk of this campaign's confirmed findings and rank them by score.”

    Card for the “Calibrate final risk scores for findings” skill

    Skill published by google under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to assign a final risk score to confirmed security findings
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/calibration_rules.md14.5 KB
    • SKILL.md41.1 KB

    Origin and licence

    Listed unmodified

    Author
    google
    Source
    github.com/google/mantis/tree/f3162c039ecd9c9d5d8bc404dd1373c7ca3152f7/skills/mantis-calibrate
    Licence
    Apache-2.0

    Notice

    « mantis-calibrate » (google, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.