Works with the AI Agents you already use
crg context profiler
Builds structured, evidence-tagged cyber risk context profiles and asset dependency maps from documents or interviews.
$10
crg context profiler
Example session with this skill installed
We are a 200-person fintech in Ontario. Our core banking is on AWS. We use a third-party for KYC. No formal audits done yet. Start the context profile.
- Read your context and instructions
- Compiled the crg context profiler
I have initiated the Cyber Risk Context Profile based on your description. Because no formal documentation was provided, all facts are currently recorded as user assertions with weak evidence strength.
Cyber Risk Context Profile — Fintech Organization (Ontario), 2025-05-20
1. Scope and evidence register
The scope covers the next 12 months, focusing on confidentiality, integrity, availability, and compliance.
| ID | Source | Type | Strength | Supports |
|---|---|---|---|---|
| E1 | User description in chat | User assertion | Weak | Location (Ontario), Size (200), Core banking (AWS), KYC (Third-party) |
2. Organization profile
The organization is a fintech enterprise operating in Ontario with approximately 200 employees (E1).
3. Critical business processes
Information gap — organizational validation required regarding specific revenue-generating processes. Primary assumed process: Core Banking Operations.
4. Crown-jewel assets and dependencies
| Crown jewel | Purpose | Owner | C / I / A | Depends on | Consequence of loss | Evidence |
|---|---|---|---|---|---|---|
| Core Banking System | Financial transactions | Gap | High / High / High | AWS Cloud; Identity Provider | Total operational halt; financial loss | E1 |
| KYC Data | Regulatory compliance | Gap | High / Low / Low | Third-party KYC Provider | Regulatory fines; onboarding halt | E1 |
Management decision required.
7. Maturity snapshot
| Function | Level | Evidence |
|---|---|---|
| Govern | Not evidenced | No evidence provided |
| Identify | Level 1 - Initial | E1 (Basic asset identification) |
| Protect | Not evidenced | No evidence provided |
8. Candidate legal obligations
| Instrument | Why it may apply | Condition from legal.json | Status |
|---|---|---|---|
| PIPEDA | Private sector org in Ontario | Commercial activity involving personal info | to confirm by legal counsel |
9. Information gaps and next steps
| # | Gap | Question to close it | Who can answer | Blocks |
|---|---|---|---|---|
| 1 | Asset Ownership | Who is the business owner for the Core Banking system? | CTO/COO | Responsibility mapping |
| 2 | Control Evidence | Do you have a SOC2 or internal security policy? | CISO | Maturity snapshot |
This profile supports, and does not replace, management’s decision.
Next steps
- Review and validate the "Analytical estimate" markers in Section 4.
- Provide security policy documents to upgrade Evidence Strength from "Weak".
- Confirm the crown jewel list to proceed to the Risk Appetite step.
Connects securely to your tools. The creator never sees your data.
About this skill
Risk assessments fail when they are built on shaky assumptions rather than documented facts. This skill enforces a structured discovery process to establish the organizational context, assets, and evidence required for a valid cyber risk profile.
What it does
- Evidence-backed profiling builds a register of documents, interview answers, and audit findings, assigning a strength rating to every source.
- Crown jewel identification maps critical business processes to their underlying technical dependencies and single points of failure.
- Maturity snapshots evaluates organizational capabilities across Govern, Identify, Protect, Detect, Respond, and Recover functions.
- Legal screening identifies candidate regulatory obligations based on jurisdiction, sector, and data types.
- Gap analysis flags missing information and blocks to progress, preventing the use of "typical" sector data to fill blanks.
How it works
- Intake phase analyzes provided documents or initiates an interview mode to extract organizational facts.
- Fact structuring populates the evidence register and maps dependencies for assets confirmed as "crown jewels."
- Drafting generates a structured profile in English or French using the CyberRiskGuardian methodology.
- Validation marks all assumptions, analytical estimates, and gaps for management review.
Frameworks & tools
This skill implements the CyberRiskGuardian method (Steps 1 to 3). It utilizes the dss/v1 risk-context contract and supports exports compatible with JSON schemas for downstream risk tools.
Why this beats prompting it yourself
Generic prompts often hallucinate asset lists or maturity levels when data is missing. This skill strictly enforces evidence-tagging, ensuring that every claim in the profile points back to a numbered source (E1, E2) or is explicitly marked as a gap.
Use cases
- Start a formal cyber risk assessment for a new client or department.
- Convert unstructured interview notes into a structured evidence register.
- Identify concentration risks and single points of failure in third-party dependencies.
- Screen an organization for applicable legal instruments like Québec's Law 25.
Known limitations
This skill does not score risks, calculate probabilities, or provide legal opinions. It refuses to record individual secrets, keys, or PII, requiring population-level generalizations instead.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
No risk scoring or probability estimation. Requires manual validation of all analytical estimates. Refuses PII, secrets, or individual account names. English and French only.
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 buying a skill.
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