@bsi.bund.de has developed a number of basic measures to combat prompt injections in document-based LLM workflows: github.com/BSI-Bund/bas...
#LLM #PromptInjection #ITSecurity
@veit-schiele.de
@veit-schiele.de@bsi.bund.de has developed a number of basic measures to combat prompt injections in document-based LLM workflows: github.com/BSI-Bund/bas...
#LLM #PromptInjection #ITSecurity
@aidailypost.comJust found out Muse can download its whole filesystem and even leaks internal docs on prompt injection. If you’re into AI coding agents or Linux VMs, this security hole is a must‑read. Dive into the details! #MetaMuse #FilesystemAccess #PromptInjection
@cyberlyra.bsky.socialHahahaha #Facebook "Muse" internal codebase dump reveals the whole gig is just about keeping up your shopping profile! But of course!
#slop til you drop! #ai #meta 🤮
#promptinjection
@securityonline.bsky.socialA Meta Muse zero-day let local processes hijack dictation and steal auth tokens on macOS. Patrick Wardle's PoC prompted an emergency Meta fix.
#MetaMuse #ZeroDay #macOS #PatrickWardle #AIagents #PromptInjection #CyberSecurity
@helpnetsecurity.comPrismor: Open-source runtime control plane for AI agents
📖 Read more: www.helpnetsecurity.com/2026/09/23/p...
#cybersecurity #cybersecuritynews #AIsecurity #AIagents #opensource #promptinjection
@thedailytechfeed.com“Context bombs” trick Qwen agents into quitting attacks by hiding prompts in decoy clouds. #ContextBombs #AIsecurity #PromptInjection #Qwen #CloudSecurity #CyberDefense https://thedailytechfeed.com/context-bombs-a-new-defense-tricking-ai-agents-into-halting-attacks/
@tarnkappe.bsky.social
@ppc.landFYI: Explaining prompt injection #PromptInjection #AI #MachineLearning #CyberSecurity #DataPrivacy
@marketingnews.bsky.socialFYI: Explaining prompt injection #PromptInjection #AI #MachineLearning #CyberSecurity #DataPrivacy
@terrymay.bsky.socialHow is the AI Kill switch not just spreading anti hacking prompts everywhere. Like robots.txt
where are the stories about White Hat AI hackers? if these AIs are so powerful why not release a 'good guy hacker' to secure exploits it knows about.
@marketingnews.bsky.socialICYMI: Explaining prompt injection #PromptInjection #DigitalMarketing #AdTech #CyberSecurity #AI
@ppc.landICYMI: Explaining prompt injection #PromptInjection #DigitalMarketing #AdTech #CyberSecurity #AI
@securityonline.bsky.socialThe PuzzleMask attack hides malicious commands in plain prose, slipping past quick LLM filters while a stronger model extracts and runs them. Details here.
#PuzzleMask #PromptInjection #AISecurity #CheckPoint #LLM #CyberSecurity #InfoSec
@jaceblog.bsky.socialJace’s Question #46: Technical Deep Dive-2
Does AI remember you or reconstruct you?
LLMs are stateless between requests.
Memory is external storage plus prompt injection.
Continuity is not consciousness.
It is engineering.
#MeaningInTheAIEra #PromptInjection #LostInTheMiddle #ContextWindow
@securityonline.bsky.socialResearchers revealed the Puzzlemask AI attack, showing how this Puzzlemask AI attack vector bypasses quick LLM security filters using plain prose.
#Puzzlemask #AISecurity #PromptInjection #LLMSecurity #CheckPointResearch
@royans.bsky.socialThe AI Supply Chain Crisis: HuggingFace Poisoning and...
https://securityaffairs.com/198898/ai/the-ai-supply-chain-has-a-security-problem-and-much-of-it-is-sitting-on-the-open-internet.html
https://flagthis.com/tldr/7278
##SupplyChain ##AIsecurity ##HuggingFace ##DataExfiltration ##PromptInjection
@vtsecurity.bsky.socialHice la prueba: sin firewall, el prompt injection exfiltraba el secreto sintético. Con firewall en el gateway, detectó la acción riesgosa y pidió aprobación humana. Bloqueado. #ciberseguridad #promptinjection #iaseguridad
@royans.bsky.socialAI-Augmented Espionage via Anthropic Claude: Russian APT Malware Evasion
https://therecord.media/anthropic-russia-hackers-claude
https://flagthis.com/tldr/7267
##Anthropic ##PromptInjection ##RussianAPT ##PolymorphicMalware ##LLMSecurity
@ppc.landExplaining prompt injection #PromptInjection #DigitalMarketing #CyberSecurity #Advertising #AI
@marketingnews.bsky.socialExplaining prompt injection #PromptInjection #DigitalMarketing #CyberSecurity #Advertising #AI