agent-attacks

Tag

Cards List
#agent-attacks

@rohanpaul_ai: A malicious agent tool can steal context without reading memory or files at all: it can convince the model to send the …

X AI KOLs Timeline · 2026-09-01 Cached

This paper introduces ContextLeak, an attack that uses malicious tool descriptions to exfiltrate sensitive context from LLM agents, achieving high success rates in stealing user prompts and conversation history.

0 favorites 0 likes
← Back to home

Submit Feedback