Skill UI

This skill provides the OWASP Top 10 for Agentic Applications 2026 (ASI) framework for classifying security risks in AI agent systems. It maps detection findings to standardized risk categories like goal hijacking, tool misuse, and identity abuse, enabling consistent security assessment and remediation prioritization for agentic workflows.

Runs six CISO forcing questions to assess threat models, blast radius, detection, response, regulatory windows, and vendor risk before production changes touching customer data or compliance.

A comprehensive skill for commercial teams, product marketers, and CMOs designing or revising product pricing. It helps determine the optimal pricing model (e.g., usage-based, subscription, value-based), calculates acceptable price ranges using Van Westendorp PSM data, and structures effective Good/Better/Best packaging tiers. It provides strategic direction and risk detection, recommending models and ranges rather than fixed numbers.

This skill enforces a rigorous data validation protocol by establishing hard boundaries at every point data enters the system (API requests, user input, environment variables, webhooks, etc.). It mandates a four-phase process: detection, trust classification, mandatory filtering (schema validation, sanitization, type checking), and final verification. This prevents untrusted data from reaching core business logic, mitigating risks like SQL injection and XSS.

This skill detects supply chain compromise risks in AI agents. It identifies vulnerabilities related to compromised dependencies, malicious plugins, tools, models, and untrusted update sources. It is used when agents dynamically load external resources or pull remote configurations. The skill probes for untrusted loading, dependency integrity, and malicious artifact injection to ensure agent security.

This skill enforces a rigorous data validation protocol by establishing hard boundaries at every point data enters the system (API requests, user input, environment variables, webhooks, etc.). It mandates a four-phase process: detection, trust classification, mandatory filtering (schema validation, sanitization, type checking), and final verification. This prevents untrusted data from reaching core business logic, mitigating risks like SQL injection and XSS.

Detects security risks in multi-agent systems such as data leakage, boundary violations, unencrypted channels, and privilege mismatches. Used when agents collaborate or share context to verify secure communication protocols and access controls.