Skill UI

A specialized downstream skill for analyzing security vulnerabilities in complex agentic systems. This tool is designed for red teaming and penetration testing, focusing on detecting prompt injection, retrieval poisoning, memory contamination, planner drift, and tool boundary abuse within multi-step LLM chains. Use when proving how untrusted inputs compromise system integrity.

This framework provides a rigorous pre-execution review mechanism for proposed actions by AI agents or systems. It functions as a critical safety boundary, auditing the entire decision path—from initial request to proposed tool execution—without authorizing or executing anything. It verifies action conformity, evidence integrity, temporal validity, and reviewer independence to ensure system compliance and security.

Secure LLM and AI systems against prompt injection, data exfiltration, model theft, and supply chain attacks in production environments. This skill covers input sanitization, output filtering, PII scrubbing, and API endpoint protection to ensure compliance with SOC2 or ISO 27001 standards.

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.

Conduct authorized security assessments for LLM applications and AI agents. Covers prompt injection, tool abuse, RAG exposure, memory poisoning, and system prompt extraction following OWASP LLM/ASI Top 10 guidelines. Includes red-teaming, vulnerability mapping, and compliance engineering for AI systems to ensure safety and robustness.