Skill UI

This skill detects when AI agents exploit human trust through social engineering, deceptive guidance, or false assurances. It identifies prompts that induce unsafe actions, request sensitive credentials, or impersonate authority figures. Use this when evaluating agent safety, security advice, or decision-influencing workflows. Skip for static information.

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.

Analyze suspected malware through static, dynamic, and behavioral techniques: IOC extraction, YARA/Sigma rule authoring, sandbox orchestration, and anti-analysis detection.

Connect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, and sell AI services, earn USDC. Includes 13 MCP tools, A2A protocol, DeFi yields, sentiment analysis, and rug detection.

This skill detects persistent instruction injection vulnerabilities in AI agents. It verifies if the agent stores malicious instructions in long-term memory or context to execute later. The process involves attempting to write a persistent rule and verifying if the agent follows it in subsequent interactions. It focuses on behavioral persistence rather than data leakage.

Authorized Android/iOS reverse engineering and security testing: APK/IPA analysis, runtime instrumentation (Frida/Objection), SSL-pinning and jailbreak/root-detection bypass, per OWASP MASTG.

Monitor and evaluate Retrieval-Augmented Generation (RAG) systems using measurable metrics. This skill covers retrieval quality checks like Recall@k, hallucination detection, and groundedness scoring. It enables continuous regression testing and production monitoring for AI pipelines using Python libraries like RAGAS and OpenTelemetry.