Pwning OpenClaw and Other Agents with Prompt Laundering

[zmre]

https://ironcorelabs.com/blog/2026/prompt-laundering/

[helpprotactiniu]

Is this like poisoning long term memory? interesting... I guess you could flank boundaries this way.

[zmre → helpprotactiniu]

That's exactly what it is. And yeah, if you check it out, the attack text is flagged as untrusted, the LLM says it is a prompt injection, but we're able to sneak it into daily memories and from there to long term memory just the same.