Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    crg ai agent risk

    1

    Generates structured cybersecurity risk scenarios for AI agents and LLMs using CRGO and OWASP frameworks.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    crg ai agent risk

    crg ai agent risk

    Example session with this skill installed

    Generate risk scenarios for a RAG-based HR assistant. It uses a self-hosted Llama 3 model, reads internal employee PDF folders, and acts with approval to draft emails to candidates. No logs.

    • Read your context and instructions
    • Compiled the crg ai agent

    The risk analysis for the HR assistant is complete. I have mapped the autonomy levels, identified potential injection vectors via untrusted document ingestion, and provided a management priority list.

    1. AI inventory

    SystemPurposeModelAutonomyTools and permissionsData read / writtenUntrusted contentOversightSupply chainEvidence
    HR AssistantRecruitment supportLlama 3 (Self-hosted)Acts with approvalDraft e-mailEmployee records (Sensitive)Uploaded CVs/PDFsHuman-in-the-loopLocal model deploymentE1

    2. Pattern and OWASP mapping

    SystemCRGO patternOWASP id and CRGO labelWhy it applies
    HR AssistantPatPromptInjectionLLM01:2025 manipulation by injected instructionsIngests untrusted PDFs from candidates
    HR AssistantPatAgenticMisuseASI01:2026 redirection of an agent's goalsAccess to internal employee folders via RAG

    3. Risk scenarios

    AI-S1: A candidate uploads a CV containing hidden system instructions (threat source) → the RAG system processes the prompt injection (weakness) → HR Assistant and employee folders (asset) → the agent exfiltrates internal salary data into a drafted email (event) → privacy breach and regulatory non-compliance (consequence).

    Analytical estimate — validation required.

    5. Priority list for management

    RankScenarioTierReasonDecision for managementMarker
    1AI-S1HighSensitive data access + untrusted inputImplement robust input filtering for PDFsManagement decision required

    Quantification is not performed here; a separate quantification step is needed.

    Next steps

    • Validate the sensitivity classification of the employee PDF folders.
    • Review the recommended SP 800-53 controls for least privilege access.
    • Perform a formal quantification of the potential regulatory fines.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    AI agents and LLMs introduce unique security failures, from prompt injection to excessive autonomy. This skill structures cybersecurity risk scenarios for your AI inventory using the CyberRiskGuardian method, mapping your systems to CRGO patterns and OWASP LLM/Agentic identifiers. It converts raw technical specs into structured causal chains and management-ready priority lists to support pre-deployment reviews and risk registers.

    What it does

    • AI Inventory Mapping builds a detailed table of models, autonomy levels, tool permissions, and data flows.
    • Pattern Identification maps assets to CRGO patterns like PatPromptInjection, PatAgenticMisuse, and PatAISupplyChain.
    • Causal Scenario Writing generates structured chains linking threat sources and weaknesses to specific operational consequences.
    • Control Gap Analysis compares your existing safeguards against recommended NIST SP 800-53 and CIS v8.1 controls.
    • Management Prioritization produces a qualitative risk list (High, Medium, Low) for executive decision-making.

    How it works

    1. Supply an inventory of your AI systems, including model types, tools, autonomy levels, and data sensitivity.
    2. The agent identifies information gaps and marks assumptions for organizational validation.
    3. It generates a full risk report with six mandatory sections, including OWASP mappings and ATT&CK technique IDs.
    4. Review the management priority list to identify where human approval gates or kill switches are required.

    Frameworks & tools

    This skill utilizes the CyberRiskGuardian risk method, OWASP Top 10 for LLM (2025) and Agentic AI (2026), NIST SP 800-53, MITRE ATLAS, MITRE ATT&CK, and CIS Controls v8.1.

    Why this beats prompting it yourself

    Generic prompts fail to maintain the rigorous causal chain required for formal risk assessments. This skill enforces specific taxonomy from the CRGO ontology, ensuring that every risk is mapped to industry-standard IDs rather than vague descriptions.

    Use cases

    • Conduct a pre-deployment security review for an autonomous CRM-linked agent.
    • Draft a formal AI risk register for compliance with ISO/IEC 42001 or 23894.
    • Analyze the supply chain risks of using third-party MCP servers or plugins.
    • Brief management on the impact of prompt injection on internal RAG assistants.

    Known limitations

    Does not perform quantitative risk analysis, financial modeling, or CVSS scoring. It excludes model bias, fairness assessments, and penetration testing instructions.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Requires a manual AI inventory input. Qualitative tiers only; no probability or dollar values. Does not provide ISO/IEC 42001 clause text or conformity statements.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    Permissions

    Read Files
    Write Files
    Network Access
    Listed7 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the creation of formal risk registers by mapping your specific AI architecture to the CyberRiskGuardian (CRGO) ontology and OWASP standards, ensuring technical vulnerabilities are translated into clear, management-ready causal chains.

    The skill supports any LLM-based system, including RAG assistants, autonomous agents, and third-party plugins, provided you can describe their autonomy levels, tool permissions, and data access.

    While it references MITRE ATLAS and OWASP Top 10 for LLM/Agentic AI, it does not perform active penetration testing or vulnerability scanning; it is a structural risk modeling and documentation tool.

    You receive the fully configured AI agent skill ready for your workspace, which includes the logic for framework mapping, causal chain generation, and the six-section risk report template.

    Yes, the skill is updated to reflect the latest CRGO patterns and evolving industry standards, such as the OWASP Top 10 for LLM (2025) and upcoming Agentic AI frameworks.

    Simply provide your AI inventory—details like model type, autonomy level, and data sensitivity—and the skill will guide you through identifying gaps and generating your first report.

    New in Security