Check Skill Security — Security skill for Claude Code
Check skills and scripts for unsafe execution, credential handling, and scope controls.
How to install Check Skill Security
Installs to ~/.claude/commands/openshift-traust-check-skill-security.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/openshift/traust/HEAD/.claude/commands/check-skill-security.md -o ~/.claude/commands/openshift-traust-check-skill-security.md Restart Claude Code, or start a new session, for it to be picked up.
What Check Skill Security does
description: "Check skills and scripts for unsafe execution, credential handling, and scope controls."
Run the skill security-posture gate using the check-skill-security skill. Load the skill at .claude/skills/check-skill-security/SKILL.md and follow it: run python3 -m traust.cli tools check-skill-security from the harness root, report each violation with its rule id, file, and the audit finding class it guards, and walk the user through the prescribed fix pattern for every rule that fi
Alternatives in Security
- Security Guidance — Hook that warns about command injection, XSS, and unsafe patterns 14k ★
- Security Guardian — Comprehensive security analysis for RTK CLI tool, focusing on command injection, shell escaping, hook security 11.9k ★
- Skills Audit Report — Date: 2026-02-15 Auditor: Automated Skill Quality Audit Scope: Recently added skills in business-growth/, fina 5.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Review AI Agent Surface
Audit the AI and agent attack surface: prompt injection, tool-permission scope, unbounded agent loops, and uns
Security Check
Scan project for security issues — exposed secrets, missing .gitignore entries, unsafe patterns
API QA
Use when testing API endpoints for contract compliance, error handling, security, and performance. Covers 'tes
Vibe Check
Production resilience audit for AI-generated code. Catches edge cases, scale failures, and missing error handl
Openclaw Ops
OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans.
Openclaw Config Pack
Hardened configuration pack for OpenClaw personal AI assistant — 9-layer security, Telegram topics, plugins, s
Related Agents
Light Security ClaudeSettingsAudit
Audit Claude Code config files (settings.json, settings.local.json, .mcp.json) for unsafe or malicious content
Reliability Availability Review
Reviews a diff for reliability/availability defects — error handling that hides failure, missing timeouts/retr
Gitnexus Security Boundary Reviewer
GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,