Phying News
P非影 中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Special Token Injection (STI) Attack Guide

blog.sentry.security | blog | #ai-security | #pentesting | #prompt-injection | #llm | #special-token-injection | #chatml

Summary

A pentester's guide to Special Token Injection (STI): reserved tokens and chat templates, when poorly escaped, let attackers override system prompts, forge roles, and hijack tool calls in LLMs.
Published
Collected

original ↗

Related coverage

  1. Living off Someone Else's Inference (blog.sentry.security)
  2. Exploiting Tool and Function Calling in LLM Agents (blog.sentry.security)
  3. Semantic vs. Token-Based LLM Injections (blog.sentry.security)
  4. LLM API Misconfigurations (blog.sentry.security)
  5. When to use SAST versus an LLM security scanner (about.gitlab.com)
  6. What’s changed in AI security over the past two years (bugcrowd.com)

back