Prompt Injection Guard — Development skill for Claude Code
Detect prompt injection, hardcoded secrets, destructive commands and exfiltration patterns in any text or file.
How to install Prompt Injection Guard
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zhaoxinghua09-cell/prompt-injection-guard and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Prompt Injection Guard does
Detect prompt injection, hardcoded secrets, destructive commands and exfiltration patterns in any text or file. 检测提示注入、硬编码密钥、破坏性命令与数据外泄模式。
Alternatives in Development
- Sanitize — Detect and redact PII from text files — 15 categories (SSNs, credit cards, API keys, etc.), zero dependencies 3.1k ★
- Careful — Activate destructive command warnings for the session 2.8k ★
- SwiftUI Microinteractions — One command in Claude Code, Cursor, or Codex and your agent already knows the physics, the spring curves, and 110 ★
README
Prompt Injection Guard (提示注入检测器)
**Fail-closed prompt injection / malicious-instruction scanner with threat taxonomy.** **基于威胁分类法的提示注入/恶意指令扫描器，fail-closed。**
[](https://github.com/zhaoxinghua09-cell/prompt-injection-guard) [](LICENSE) [](CONTRIBUTING.md)
Usage / 用法
python scripts/prompt_guard.py [--json] [--badge out.svg]License
MIT (code) · All rights reserved (SKILL.md theory text). © 2026 Steven Zhao / SynomosAI.
Related Skills
Narthex
Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration
ClaudeG
Claude Code skill: guard rails against weakened tests, unverified 'fixed' claims, placeholders, destructive co
Skill Scan Gate
CI gate for Claude Code skills and plugins: scans a skills or plugin repository for instruction-override text,
Destructive Guard
Claude Code plugin: detect destructive/deletion bash commands → y/n confirmation (works in bypassPermissions)
Danger Guard Plugin
Deterministic pre-exec interception of destructive shell commands for OpenClaw agents. Gateway-level pattern m
Cua Hunt
Hunt Computer-Use-Agent (CUA) prompt-injection surface — instructions planted in CUA-readable DOM channels (hi
Related Agents
AI Code Security Auditor
Security reviewer for AI-generated and vibe-coded apps — hunts the hardcoded secrets, broken row-level securit
Security AI Generated Code Auditor
Security reviewer for AI-generated and vibe-coded apps — hunts the hardcoded secrets, broken row-level securit
Appsec Secure Codegen Reviewer
Use to review AI/model-generated or newly written code for insecure-by-default patterns: injection sinks, unsa
