Prompt Injection Auditor
Security audit skill for LLM agents - prompt injection scanner, attack catalog & defense checklist
screem500 · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add screem500/prompt-injection-auditor技能说明
prompt-injection-auditor
An open Agent Skill that turns any AI agent into a prompt-injection security auditor. Static scanner + attack catalog + defense checklist + authorized red-team payloads — built against real-world incidents like EchoLeak (CVE-2025-32711).
Works with Claude Code, Cursor, Kimi, and 20+ agents that support the open Agent Skills standard.
Measured: separation between hardened and vulnerable prompts improved from 8.3 to 40.6 points, with zero false positives on the hardened corpus. See VALIDATION.md.
Why?
Prompt injection remains unsolved: there is no general defense, and every published mitigation is probabilistic. Real incidents keep proving it:
- EchoLeak (CVE-2025-32711, CVSS 9.3) — the first zero-click prompt injection in a production AI system: hidden instructions in an email made Microsoft 365 Copilot exfiltrate OneDrive/SharePoint data via a markdown image, no clicks needed.
- LangGrinch (CVE-2025-68664, CVSS 9.3) — LangChain Core serialization injection: unescaped
lckeys let LLM-influenced data be rehydrated as objects, enabling secret extraction. The flaw sits in the serialization path, not deserialization. LangChain.js carries the parallel CVE-2025-68665 (CVSS 8.6). - Langflow (CVE-2025-3248 / CVE-2026-33017) — unauthenticated RCE in an agent-building framework; the 2026 flaw was exploited in the wild within 20 hours of the advisory, before any public PoC existed. Note that 1.8.2 was widely reported as fixed but remained exploitable — only 1.9.0+ is verified.
In 2026 the threat moved from fra