… While some AI assistant tools like Claude Cowork won’t train their models on your data, your file could still be at risk from “prompt-injection” attacks–that is, files with hidden prompts that could trick Claude or another AI into uploading sensitive information to the attacker. …
… For example, the big AI providers may use your inputs as training data for their models, and there’s also the risk of your confidential info slipping out into the wild via prompt-injection attacks and other exploits. …
… Anthropic says Claude is trained to detect if it’s being subjected to a prompt injection attack. …
… OpenClaw is also worryingly vulnerable to “prompt injection” attacks, which aim to trick an LLM into ignoring its guardrails and do things like leak your private data, install a backdoor on your system, or even execute a root-level “rm -rf” command on your system, which would nuke your entire hard … …