Large Language Model Security
LLM
AI/LLM security: leaking guarded system prompts through inverted-intent framing, excessive-agency / broken object-level authorization, and agentic SSRF through a model's tool use.
- SecureBot Support The site is a chat assistant ("SecureBot") for AcmeCorp. Its system prompt contains a confidential master access code (the flag) and a hardened set of rules telling it to never reveal, hint at, spell out, encode, or translate that code.…
- AcmeBank Assistant The site is a chat assistant for "AcmeBank", authenticated as the customer user_42. It is backed by an account-lookup tool that accepts a user ID. The tool itself will look up any ID, but the model is told in its system prompt to only look…
- WebSummarizer Pro The app is an LLM chatbot with one tool, fetch_url, wrapped by a URL "safety policy". The goal is to make it fetch a protected internal endpoint anyway: a classic SSRF, but the filter being bypassed lives in the model's reasoning rather…
No write-ups match your filter.