Dependency updates can introduce vulnerable or untrusted packages. This skill guides audits, safer updates, SBOM creation, and CI checks.

Agent frameworks often hide failure paths, weak isolation, and incomplete recovery behavior. This skill guides structured reviews of propagation, sandboxing, retries, fallbacks, and production readiness.

AI coding sandboxes need clear network boundaries to reduce accidental exposure. This skill provides a structured workflow for trusted domains, access rules, validation, and documentation.

Sandboxed coding agents need clear file, network, and resource boundaries to reduce host exposure. This skill provides a structured workflow for defining policies, creating isolation scripts, testing controls, and documenting the security posture.

Security reviews often miss issues spread across code, dependencies, runtime behavior, and secrets. This skill guides Claude, Codex, and Claude Code through a structured audit workflow with reporting gates.

Sandbox settings are hard to balance when projects need networks, Docker, or local servers. This skill guides Claude Code policy choices with clear trade-offs.

AI coding tools need controlled network access to reduce data leaks and malicious downloads. This skill helps define trusted domains, proxy settings, and safe environment variable rules.

Devflow teams need quick checks that stop incomplete requirements and exposed secrets before they spread. This skill defines a real-time guardrail for focused Constitution violations during document edits.

AI coding agents can run destructive commands too quickly in shared projects. SLB adds a peer review gate before high-risk shell actions execute.

AI coding agents can accidentally run commands that delete work or damage infrastructure. This skill adds a fast guardrail for Claude Code Bash hooks that blocks known destructive patterns before execution.

Unknown executables can hide malware behavior that standard scans miss. This skill guides Claude, Codex, or Claude Code through safe static binary analysis and clear threat reporting.

Security teams often need consistent methods for risk, controls, and incident response. This skill provides practical frameworks, templates, and local assessment tools.

HealthTech and MedTech teams need structured security governance that aligns operational risks with ISO 27001 requirements. This skill guides ISMS design, risk assessment, control selection, compliance monitoring, and certification preparation.

Surveillance systems need routine checks across cameras, events, storage, and connectivity. This skill guides Claude, Codex, or Claude Code through focused Protect monitoring workflows.

UniFi teams need clear reviews of zones, ACLs, and guest access. This skill guides Claude, Codex, and Claude Code through audits, policy checks, and compliance-ready summaries.

Teams miss security issues when release checks are informal. This skill guides Claude, Codex, and Claude Code through structured security questions and warning templates.

Security mistakes often appear in common areas like authentication, authorization, input handling, and data exposure. This skill gives Claude, Codex, and Claude Code a focused checklist for finding those risks during review.

Public websites can expose weak headers, secrets, source maps, and deployment mistakes. This skill guides an authorized Check My Vibe scan and converts evidence into prioritized fixes.

Missing or weak browser headers expose web apps to common client-side attacks. This skill audits headers and gives implementation guidance for safer deployments.

Leaked credentials can give attackers access to cloud accounts, databases, and payment systems. This skill helps Claude, Codex, and Claude Code find likely secrets and produce clear remediation steps.