PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

How a Prompt Injection Vulnerability Led to Data Exfiltration

hackerone.com | vulnerability | #ai-security | #prompt-injection | #jailbreak | #llm-security | #llm | #owasp | #genai | #data-exfiltration
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

HackerOne explains how prompt injection, ranked the top LLM risk by OWASP, lets attackers override system instructions via direct or indirect inputs, causing data exfiltration and compliance fallout.
Published
Collected

Related coverage

blog · blog.sentry.security
ChatML Role Injection (CRI)
Attackers can inject system roles into ChatML message arrays to override developer instructions, invoke hidden tools, and pad payloads for denial-of-wallet DoS; strict schema validation is key.
vulnerability · netspi.com
Exploiting a Generative AI Chatbot – Prompt Injection to Remote Code Execution (RCE)
NetSPI built a deliberately vulnerable LLM chatbot to demonstrate prompt injection risks. The walkthrough shows how injected prompts enable data disclosure and, with code execution features, RCE.
blog · blog.sentry.security
PIChef. A tool for Prompt Injection inspired by CyberChef
# PIChef. A tool for Prompt Injection inspired by CyberChef #### Sentry 08 Oct 2026 — 6 min read Share Baba Yaga represents PIChef as a keeper of dangerous recipes, mixing strange prompt-injection...
research · projectdiscovery.io
How abliterated models can get you pwned
# How abliterated models can get you pwned Oct 6, 2026 · Prince Chaddha Any open model whose weights have been edited can carry a backdoor, whether it's a task-specific fine-tune, a merged adapter...
research · wiz.io
Inside 90 days of attacks on AI infrastructure
This research provides real-world threat telemetry on how attackers target modern AI deployments and MCP interfaces.
tool · github.com
LLM SecRange: Open-Source Penetration Testing Playground for Large Language Models & Vulnerable Agents
Offers security researchers and penetration testers an out-of-the-box, comprehensive environment to practice prompt injection, OWASP LLM Top 10 risks, and agent tool-abuse exploitation against real models.
Back