review-securityReview code changes with Security Review subagent.
Install via ClawdBot CLI:
clawdbot install eohmig/review-securityGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/user/eohmigAudited Oct 9, 2026 · audit v1.0
Generated Oct 9, 2026
A platform team wires /review-security into their pull request workflow so that every proposed change is scanned by the security-review subagent before merge. The subagent inspects branch changes against the repository's default base branch, returning a severity-sorted table of findings that reviewers can resolve. This catches vulnerabilities like hardcoded secrets, injection flaws, and unsafe dependency usage before they reach production.
A security engineer uses the skill to validate external contributor patches submitted through a bug bounty or open-source contribution program. By checking out the PR branch and running the review, they quickly determine whether the submitted change introduces new vulnerabilities or requires deeper manual inspection. The structured output lets the engineer prioritize high-severity findings and communicate remediation steps back to contributors.
An on-call engineer needs to ship a critical production hotfix at 2 AM and runs /review-security on the hotfix branch before deploying. The skill compares the branch against the established base branch, surfacing any overlooked issues such as debug credentials or permissive CORS settings. A concise no-issues status gives the engineer confidence to proceed while the full findings table documents the review for post-incident analysis.
An engineering enablement team incorporates the skill into onboarding exercises where junior developers submit deliberately vulnerable code branches for automated review. The skill's severity-sorted findings teach newcomers how to identify and classify common security weaknesses. Because the subagent computes the diff automatically, trainers can focus on teaching rather than setup, and a Git history documents each exercise.
A fintech or healthcare engineering group uses /review-security as part of their SOC 2 or HIPAA change-management controls. Every production-bound branch receives a recorded security review before merge, and the resulting findings table becomes audit evidence. When an auditor asks how vulnerabilities are detected pre-deployment, the team can point to the consistent, repeatable subagent workflow.
The skill is embedded as a golden-path security review step inside an internal developer platform used by all product teams. Platform engineers maintain a single, versioned invocation of the security-review subagent, reducing duplicated toolchain configuration. Adoption is driven by making secure review the easiest path to production.
A vendor packages the skill as an optional tier in a cloud IDE or Git hosting product, where customers toggle automated security reviews on per repository. The vendor handles subagent orchestration, retention of findings, and integration with pull request comments. Customers pay a per-seat or usage-based fee for continuous automated security coverage.
The skill is distributed as part of an open-source security agent framework, with a commercial support plan for enterprises that need SLAs, air-gapped deployments, and custom rule integration. Teams adopt the free skill, then purchase support when their compliance requirements grow. Revenue comes from support contracts, training, and enterprise feature licensing.
💬 Integration Tip
Pre-check out the target branch before invoking the skill so the subagent reviews the correct code, and pass Base Branch only when comparing against a non-default base. Keep the default 'branch changes' mode for routine PR review and reserve 'uncommitted changes' for dirty working-tree checks.
Scored Oct 9, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.