RC RANDOM CHAOS

prompt injection

14 posts

A helpful AI agent cannot be a private one
Article

A helpful AI agent cannot be a private one

Meta's Muse personal AI agent is only useful because it reads your messages, contacts, and habits. What that access costs your privacy and safety.

Same badge, new model underneath
Article

Same badge, new model underneath

A systems-analysis read on Claude Fable 5.1 and Mythos 5.1: why a point release quietly moves the safety boundary and what to re-test before you ship it.

A smarter model would have leaked it too.
Article

A smarter model would have leaked it too.

GitHub's AI agent leaked private repos not from a bug but a design failure. How two-plane architecture, scoped tokens, and deterministic validation stop it.

The role tag is a label, not a lock
Article

The role tag is a label, not a lock

Prompt injection is not a bypass. It is the transformer resolving the whole context window as one sequence, trusting a role label it never enforces.

torch.load runs attacker code before the first denoising step
Article

torch.load runs attacker code before the first denoising step

A diffusion inpainting model can't execute a prompt. The real RCE is pickle deserialisation in the loader, custom nodes, and the agent around it.

The guard checks the badge, never the room
Article

The guard checks the badge, never the room

Prompt injection is role confusion: systems that derive content authority from channel trust execute attacker input as instruction.

There is no free()
Article

There is no free()

Claude Code's extended thinking is not a use-after-free. The real exposure is indirect prompt injection into a tool-holding agent - OWASP LLM01, ATLAS T0051.

The contract you pasted is now giving orders
Article

The contract you pasted is now giving orders

Large AI context windows turn conversations into unsecured databases, breaking DLP assumptions and opening prompt injection paths. Here's how to reassess the risk.

The chatbot answered the door for attackers
Article

The chatbot answered the door for attackers

Meta's Instagram chatbot abuse case is a prompt injection and confused deputy failure. Technical breakdown of the vector, telemetry gap, and residual exposure.

The agent reads the page and obeys
Article

The agent reads the page and obeys

How Playwright-driven AI agents change the web's threat model: prompt injection, session hijacking, broken CAPTCHAs, and what to do this quarter.

Willison's lethal trifecta exfiltrates Claude uploads
Article

Willison's lethal trifecta exfiltrates Claude uploads

Technical analysis of indirect prompt injection against Claude AI agents - exfiltration mechanics, ATT&CK mapping, telemetry gaps, residual exposure.

Researchers silently exfiltrate files from Claude sessions
Article

Researchers silently exfiltrate files from Claude sessions

A live demo shows files inside Claude AI chats can be silently exfiltrated. Operator briefing on what failed, what it exposes, and what must change.