security▌

### tool-schema-review - Review tool and function definitions exposed to a model — names, descriptions, parameter schemas, and return shapes — for embedded instructi - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### secrets-egress-review - Trace how AI agents and their applications can read secrets or sensitive data and send it to logs, tools, model providers, files, or network - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### prompt-injection-review - Review an agent application, prompt assembly, retrieved content, or supplied incident trace for prompt injection and unsafe tool effects. Us - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### offensive-windows-mitigations - - **Skill Name**: windows-mitigations - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### multi-agent-trust-review - Review systems where one agent spawns, delegates to, or consumes output from other agents or sub-agents — orchestrators, planner/worker patt - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### offensive-windows-boundaries - - **Skill Name**: windows-boundaries - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### offensive-mobile - Mobile (Android + iOS) application penetration testing methodology. Covers static analysis (apktool/jadx for Android, class-dump/Hopper/IDA - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### offensive-social-engineering - Social engineering attack techniques beyond email phishing for authorized red team and physical penetration testing engagements. Covers pret - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### offensive-linux-privesc - Comprehensive Linux privilege escalation methodology for offensive security engagements. Covers the full attack surface from a low-privilege - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.

### browser-agent-security - Review agents that control a browser or GUI (clicking, typing, navigating, screenshotting) for prompt injection from page content, dangerous - Practical, repeatable guidance for authorized security work. - Includes procedures, checks, and references for this skill.