Wise words from TheFireofKnowing 👇

AI agents are the next big attack surface 🤖 Watch Phantom Labs break down how enterprise agents get hijacked to leak secrets and access cloud infrastructure, even with controls in place. Free, on-demand webinar. beyondtrust.com/webinars/ai-ha… #AI #AgenticAI

Heading to Seattle BSides next month? Don’t miss Sergio Garcia’s talk on the real identity attack surface and risks hidden in Bedrock. Live demo + detection. Feb 28 @ 2 PM. Event schedule: lnkd.in/eKfKF5We #Bsides #Bedrock

Heading to Seattle BSides next week? Don’t miss Sergio Garcia’s talk on the real identity attack surface and risks hidden in Bedrock. Live demo + detection. Feb 28 @ 2 PM. Event schedule: lnkd.in/eKfKF5We #Bsides #Bedrock

We recently dove into a flaw in #OpenAI Codex to show how a simple prompt or branch name can trigger command injection. Full research here ➡️ beyondtrust.com/blog/entry/ope…

New research from Ryan Hausknecht shows how that power can quietly become command & control; blending into normal behavior while automating endpoint access. We break down architecture, abuse paths, and even detection angles. ➡️ beyondtrust.com/blog/entry/cla… #AISecurity #AIAgents

Uncovered OpenAI Codex vuln enables command injection via GitHub branch names in task creation requests. Attackers could steal GitHub user access tokens & sensitive data. Full breakdown by Tyler Jespersen:beyondtrust.com/blog/entry/ope… #OpenAI #BTPhantomLabs

Join BeyondTrust Phantom Labs™ Security Researcher, Christopher Calvani for an upcoming webinar on Understanding True Privilege in Salesforce. Mark your calendar for April 23rd: lnkd.in/eitqtBvf

𝗜 𝗯𝘂𝗶𝗹𝘁 𝗮𝗻 𝗔𝗜 𝘄𝗼𝗿𝗺 𝘁𝗵𝗮𝘁'𝘀 𝘁𝗼𝗼 𝗱𝗮𝗻𝗴𝗲𝗿𝗼𝘂𝘀 𝘁𝗼 𝗿𝗲𝗹𝗲𝗮𝘀𝗲 𝘁𝗼 𝘁𝗵𝗲 𝗽𝘂𝗯𝗹𝗶𝗰. 😈😅 When Anthropic announced that their Mythos model was too dangerous to release, the industry was shocked. 𝗜 𝘄𝗮𝘀𝗻'𝘁. Because I already knew it was