groovysecurity.bsky.social
Securing AI. Automating security. Whiteout AI — govern every AI interaction. Maestro — 15 AI agents proving what's exploitable. Secure AI Skills — 111 OWASP-audited agent skills. Built for CISOs. groovysec.com
👤 Joined on 04 April 2026
Followers
Following
Total Posts
@groovysecurity.bsky.socialSession Spotlight: “Strengthening Your AI Governance: Key Lessons and Practical Considerations from the EU AI Act, GDPR and other EU Digital Regulations” Join us at the Privacy + Security Forum, Nov. 4–6, 2026. See you in DC! bit.ly/3wnJU9h #PrivacyLaw #Cybersecurity #PrivSecForum
Show PostEU AI Act Article 50 transparency duties have applied since Aug 2. A signature on the Code of Practice isn't a label users actually see. Where does your product sit on my Disclosure Default Ladder: Absent, Available, Default, or Structural?
Show PostBy tricking AI chatbots into ignoring their own rules, attackers are bypassing enterprise security with plain English. Here is how prompt injection works—and how companies can stop it.
Show PostChris means "More concerning is that corporations don't prioritise cybersecure logging of both software development & code execution." We do have such records in better-regulated industries eg automotive, tho lately #Tesla started banning car owners from accessing locally-stored records post crash.
Show PostVery interesting! Now let’s be sensible about this, there have been no incidents with this. But it’s interesting enough to consider self-replicating worm-like prompt injections. Fusing old threats with new. Nice! alignment.openai.com/misalignment...
Show Post