Works with the AI Agents you already use
cyber risk scenario candidate
Generate specific, non-obvious cyber risk scenarios with structured causal chains and evidence tagging.
$5
cyber risk scenario candidate
Example session with this skill installed
Give me a new scenario candidate for a regional hospital. We use a cloud-based EHR and have a large fleet of connected infusion pumps. Existing scenario: Data breach of the EHR via stolen admin creds.
- Read your context and instructions
- Compiled the cyber risk scenario
I have developed a new risk scenario candidate focused on your medical device fleet, which is distinct from your existing EHR data breach scenario.
Compromised legacy infusion pump maintenance gateway disrupts inpatient care
Statement: Because an external actor can exploit unencrypted management protocols on a legacy maintenance gateway affecting the infusion pump fleet, a mass configuration change may occur, resulting in a suspension of bedside services and potential patient safety incidents.
Causal chain
- Threat source or hazardous event: External actor targeting legacy industrial control protocols.
- Vulnerability or predisposing condition: Maintenance gateway using unencrypted protocols assumed to lack per-device authentication (Analytical estimate – validation required).
- Affected asset or process: Connected infusion pump fleet / Inpatient medication administration.
- Cybersecurity event: Unauthorized batch modification of device configuration or firmware.
- Organizational consequences: Temporary loss of ability to administer IV medication, emergency diversion of new patients, and potential patient harm (Management decision required).
Why plausible here: The context mentions a "large fleet" of connected pumps; these often rely on centralized gateways that may use older, less secure protocols than a modern cloud EHR.
What makes it non-obvious: The threat targets the availability of physical care delivery through a maintenance vector rather than the confidentiality of the EHR data.
Evidence and assumptions: Gateway protocol security level (Analytical estimate – validation required).
Gaps: Specific model and patch levels of the maintenance gateway (Information gap – organizational validation required).
Alerts: None — differs from the existing scenario in threat source (protocol exploit vs. credential theft) and asset (infusion pumps vs. EHR).
Next steps
- Verify if the maintenance gateway requires per-device authentication for configuration changes.
- Confirm the network segmentation between the infusion pump gateway and the public internet.
- Present this candidate to the clinical engineering team to validate the operational impact.
Connects securely to your tools. The creator never sees your data.
About this skill
Generic risk assessments often fail because they rely on textbook examples like "phishing leads to ransomware." This skill generates high-fidelity, non-obvious cybersecurity risk scenario candidates tailored to your specific organizational context. It builds specific causal chains that link threat sources to business consequences without inventing organizational facts or overstepping into remediation advice.
What it does
- Causal chain modeling mapping threat sources, vulnerabilities, and assets to specific organizational consequences.
- Deduplication comparing new candidates against your existing risk register to identify overlaps in threat sources or assets.
- Evidence tagging marking every claim as an analytical estimate, information gap, or management decision to ensure data integrity.
- Bilingual support generating full reports in English or French while maintaining searchable universal alert tags.
- Context gathering automatically requesting missing sector, process, or asset details before proceeding with analysis.
How it works
- Provide your organizational context, such as sector, critical processes, and key systems.
- Optionally paste your existing risk scenarios to ensure the new candidate is original.
- The agent analyzes the inputs to identify a plausible, non-obvious threat path.
- Review the structured output including the causal chain, plausibility justification, and critical alerts.
Frameworks & tools
This tool follows cybersecurity risk management principles similar to ISO/IEC 27005 or NIST SP 800-30. It focuses on the identification phase of the risk assessment lifecycle.
Why this beats prompting it yourself
Standard prompts produce generic risks that analysts already know. This skill enforces a strict causal chain logic and forces the agent to differentiate new candidates from your current register, ensuring you find gaps in your security posture rather than repeating common knowledge.
Use cases
- Generate fresh scenario candidates for an upcoming risk workshop.
- Identify hidden risks involving third-party integrators or specific data flows.
- Stress-test an existing risk register by asking for a completely original threat vector.
- Document information gaps in your current security knowledge for further investigation.
Known limitations
Does not perform risk scoring, quantification, or remediation planning. It is restricted to one scenario candidate per request and will not provide step-by-step exploit instructions.
Does not perform risk scoring or treatment recommendations. Restricted to one scenario per request. Requires human validation for organizational facts.
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 8 days ago
Permissions
No special permissions declared or detected