A severe >>log poisoning<< vulnerability has been discovered in the popular OpenClaw AI assistant, potentially allowing attackers to manipulate the agent's behaviour through indirect prompt injection. OpenClaw, an open-source autonomous agent known for its deep system integrations and ability to manage complex tasks, has recently seen massive adoption. However, its ability to self-debug and read […] The post OpenClaw AI 'Log Poisoning' Flaw Enables Malicious Content Injection appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.
First seen on gbhackers.com
Jump to article: gbhackers.com/openclaw-ai-log-poisoning-flaw/
