
trustmebro
Bypass llm guardrails by confusing it with fabricated tool output.
adversarial-attackai-securityexploitation+3
49623 days ago

Bypass llm guardrails by confusing it with fabricated tool output.

Benchmarking framework for evaluating computer-use AI agents against multi-step indirect prompt injection, with automatic adversarial goal…

Multi-cloud security auditing tool that leverages cloud provider APIs to gather configuration data, assess security posture, and generate HTML…

HyperDeceit is the ultimate all-in-one library that emulates Hyper-V for Windows, giving you the ability to intercept and manipulate operating system…