In this episode of The Cybersecurity Defenders Podcast, we discuss some intel being shared in the LimaCharlie community.

At Black Hat USA in Las Vegas, three security researchers demonstrated how Google's Gemini AI could be hijacked to take control of smart home devices using a novel form of indirect prompt injection.
Two separate security teams - NeuralTrust and SPLX - have conducted red teaming evaluations of the newly released GPT-5, and both report serious deficiencies in the model’s security posture.
Another Black Hat story, security researchers Milenko Starcik and Andrzej Olchawa from VisionSpace Technologies presented a compelling case that hacking satellites is not only more cost-effective than deploying anti-satellite missiles, but alarmingly easy due to widespread software vulnerabilities.
Our final Black Hat story, Cisco Talos researchers disclosed five critical vulnerabilities in Broadcom’s BCM5820X series chips, used in Dell’s ControlVault3 secure enclave hardware.
CISA and FEMA have jointly announced over $100 million in cybersecurity grant funding for the 2025 fiscal year, targeting state, local, and tribal governments.

Support our show by sharing your favorite episodes with a friend, subscribe, give us a rating or leave a comment on your podcast platform.

This podcast is brought to you by LimaCharlie, maker of the SecOps Cloud Platform, infrastructure for SecOps where everything is built API first. Scale with confidence as your business grows. Start today for free at limacharlie.io.

#237 - Intel Chat: Black Hat roundup - Gemini AI, NeuralTrust & SPLX, VisionSpace Tech, BCM5820X - & CISA/FEMA grant funding