prompt-injection-detector 作者： Vishesh Agarwal
Detects hidden prompt injection instructions that might manipulate AI models like Copilot and Claude.
尚无用户尚无用户
扩展元数据
屏幕截图
关于此扩展
AI assistants like GitHub Copilot, ChatGPT, and others read web page content when you ask them to help. Attackers can hide malicious instructions in that content — invisible to you, but visible to the AI — to hijack its behaviour, steal your data, or bypass safety filters.
PromptGuard detects:
- Hidden elements (
- HTML comments — invisible to humans but read by AI tools ingesting page source
- LLM-specific formats:
Three sensitivity levels:
- 🟢 Normal — high-confidence imperative overrides only (low false positives)
- 🟠 High — adds jailbreak, DAN, developer-mode, bypass patterns
- 🔴 Ultra — adds roleplay, persona, exfiltration, and LLM prompt-format patterns
Click any finding to flash and scroll to the exact element on the page.
All scanning runs locally in your browser. Nothing is sent anywhere.
PromptGuard detects:
- Hidden elements (
display:none, visibility:hidden, zero opacity, sub-pixel fonts, same-colour text)- HTML comments — invisible to humans but read by AI tools ingesting page source
- LLM-specific formats:
[INST], system:, assistant: prompt injection patternsThree sensitivity levels:
- 🟢 Normal — high-confidence imperative overrides only (low false positives)
- 🟠 High — adds jailbreak, DAN, developer-mode, bypass patterns
- 🔴 Ultra — adds roleplay, persona, exfiltration, and LLM prompt-format patterns
Click any finding to flash and scroll to the exact element on the page.
All scanning runs locally in your browser. Nothing is sent anywhere.
评分 0（1 位用户）
权限与数据
更多信息