agents

Hey hackers - agent red teaming outgrew the prompt fuzzer somewhere between the first tool call and the first exploit chain that never touched the user's input. The scoring harness now decides what "secure" means, and modern agent red teaming lives or dies by what that harness can see. In 2026...

Hey hackers - indirect prompt injection went from research curiosity to the top line of the OWASP agentic risk register in about eighteen months. The payload never touches your prompt. It waits in an email, a web page, a log line, an ad - and the agent reads it for you. TL;DR: Google's threat...

Hey hackers - the memory poisoning of 2026 is a single adversarial write that outlives the session, the prompt, and often the vendor's own filters. A memory poisoning attack in 2026 needs no direct memory access - the agent writes the payload itself, then retrieves it next Tuesday without you in...

Hey hackers - the mcp supply chain of 2026 is one STDIO interface, ten CVEs, and a protocol vendor calling arbitrary command execution expected behavior. An mcp supply chain attack in 2026 does not need a memory corruption bug - it needs a JSON field called command, an argument called args, and...