Skill UI

This skill enables the identification and exploitation of client-side DOM vulnerabilities, including DOM Clobbering, PostMessage bypasses, Service Worker abuse, and CSS exfiltration. It is designed for authorized security assessments to discover high-value attack chains that bypass server-side filters. Users must obtain explicit written permission before testing any target.

Hunt LDAP injection and XPath injection vulnerabilities in web applications. Covers authentication bypass, blind attribute exfiltration, and Active Directory vs generic LDAP differences. Includes attack surface signals, filter grammar, and authorized-use guidance.

This skill focuses on identifying security vulnerabilities in Large Language Model (LLM) and AI features. It covers prompt injection, system prompt leakage, cross-tenant access, and data exfiltration techniques. Users must verify findings against false positives using reproducibility checks and out-of-band callbacks before reporting.

Authorized-use hunting guide for XXE vulnerabilities: maps XML entry points, tests file uploads, SAML and SOAP endpoints, then escalates from inline file read to blind out-of-band exfiltration, SSRF pivoting and internal service access.

Detects data exfiltration via URL path encoding and chained web_fetch navigation, covering fake trusted UI injection, indirect prompt injection, letter-level path exfiltration, and multi-hop navigation hijacking in agent memory/context scenarios.