# Code Safety > Scan LLM-generated code for security vulnerabilities using language-aware pattern rules Use when this capability is needed. - Skill: `tomevault-io/code-safety` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/code-safety` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/code-safety/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/code-safety --- # Code Safety Scanner A guardrail automatically scans code in your responses for security vulnerabilities. You also have a tool for on-demand code scanning. ## When to Use scan_code - Before writing code to files via write_file or create_file - Before executing code via shell_execute - When reviewing user-submitted code for security issues - Before presenting code examples that handle user input ## What It Detects - **Injection**: eval(), exec(), os.system(), command injection - **SQL Injection**: string concatenation in SQL queries - **XSS**: innerHTML, document.write, dangerouslySetInnerHTML - **Path Traversal**: unsanitized ../ in file paths - **Hardcoded Secrets**: API keys, passwords, tokens in code - **Weak Crypto**: MD5/SHA1 for passwords, Math.random for security - **Insecure Deserialization**: pickle.loads, yaml.load without SafeLoader - **SSRF**: unvalidated URL construction from user input ## Post-Approval Guardrail Override When HITL (human-in-the-loop) is enabled with `guardrailOverride: true` (the default), the code-safety scanner runs **after** HITL approval as a post-approval guardrail. This means even actions approved by a human operator or LLM judge are scanned for destructive patterns before execution. This catches accidental approvals of dangerous commands like `rm -rf /` or `DROP TABLE`. See the **hitl-safety** skill for full HITL configuration. ## Constraints - Regex-based detection — may have false positives on safe code patterns - Language detection from code fence tags or heuristics - Does not perform deep AST analysis --- > Source: [framersai/agentos-skills](https://github.com/framersai/agentos-skills) — distributed by [TomeVault](https://tomevault.io).