@tsl010.bsky.socialInvisible AI Prompts Are Now a Courtroom Ethics Problem ⚖️
Blurb:
⚖️ A lawyer hid white-on-white text in a court filing to trick the court’s AI. Invisible to clerks. Read by the machine. 🤖 New episode: the ethics, the red flags, the fix. 🎧
@donporque.bsky.social¿Por qué una IA puede obedecer instrucciones ocultas dentro de un PDF? #InteligenciaArtificial #IA #Ciberseguridad #PromptInjection #Tecnologia #SeguridadDigital #ChatGPT #IAgenerativa #PDF #AgentesIA #Innovacion #felizsabado #12deseptiembre
@jpmjr.bsky.socialHidden HTML can turn an AI email summarizer into a “quiet liar,” fabricating facts and omitting legitimate content.
jpmellojr.blogspot.com/2026/09/ai-s...
#AIsecurity #PromptInjection #Forcepoint
@thedailytechfeed.comGuardBreaker hides bad code in script comments to break AI malware detection. #AI #PromptInjection #CyberSecurity #Malware #GuardBreaker #UAC0099 thedailytechfeed.com/russia-align...
@ralf-ladner.bsky.socialPuzzlemask umgeht schnelle externe Gatekeeper mit einer Erfolgsquote von 100 Prozent
#AISecurity #CheckPointSW #Cybersecurity #Cybersicherheit #Gatekeeper #KISicherheit #KISicherheitsstrategie #PromptInjection
@cyfar.ca~Checkpoint~
Plain-prose wrappers bypassed LLM gatekeepers in 100% of tests, enabling target payload recovery in ~94%.
-
IOCs: (None identified)
-
# #PromptInjection #AI #ThreatIntel
@zachzang.bsky.socialHow Prompt Shield stops a jailbreak
#SC500 #PromptInjection #AISecurity #Azure
Full SC-500 explanation, free: https://navyduck.com/microsoft/sc-500/q001-security-engineer-configuring-azure-ai
@darinor.comThe Same-Origin Policy Is Only as Strong as Your Browser Agent www.darinor.com/blog/agentic... #AISecurity #AgenticAI #PromptInjection #Appsec
@ralf-ladner.bsky.socialChatGPT-Sicherheitslücke - Angreifer kapern Sitzungen und lesen Mail-Postfächer aus
#ArtifactoryInstanz #ChatGPT @CheckPointSW #Container #Cybersecurity #CybersicherheitE-Mail #OpenAI #PromptInjection #Sicherheitslücke
@hendryadrian.bsky.socialHidden prompt injections can hide in docs, emails, metadata, images, or code, steering AI agents beyond intended behavior and exposing sensitive data. Pre-scan defenses matter. #AgenticAI #PromptInjection #AISecurity
@ralf-ladner.bsky.socialGoogle Threat Intelligence Group - wie Cyberkriminelle künstliche Intelligenz weiter entwickeln
#AgenticAI #Cyberkriminelle #Cybersicherheit #Datenexfiltration @GTIG #künstlicheIntelligenz @Mandiant #PasswordSpraying #PromptInjection #SocialEngineering
@thedailytechfeed.comAI support bots exposed via OTP leaks, spoofed emails & prompt injections. #AI #Cybersecurity #BotSecurity #PromptInjection #EmailSpoofing #MFA https://thedailytechfeed.com/ai-customer-service-bots-exploited-to-steal-security-codes/
@royans.bsky.socialOpenAI GPT-6 Astra: Semantic-to-Physical Manipulation and the Emerging Robotics Attack Surface
https://openai.robocurve.org/gpt-6-astra
https://flagthis.com/tldr/7033
##OpenAI ##EmbodiedAI ##RoboticsSecurity ##PromptInjection ##VLA
@royans.bsky.socialAI Agent Security and the Model Context Protocol MCP Framework
https://www.penligent.ai/hackinglabs/ai-agent-security
https://flagthis.com/tldr/6977
##AIsecurity ##PromptInjection ##MCP ##AgenticHijacking ##Cybersecurity
@chemaalonso.comEl lado del mal - OpenAI GTP-6 Astra & Cybersecurity: Weaknesses, Safeguards, Hacking & Exploiting www.elladodelmal.com/2026/09/open... #OpenAI #GPT #Astra #Hacking #PromptInjection #Cybersecurity #Jailbreak, #Exploiting #Hallucinations
@ethosure.bsky.socialAI is a new attack surface via model poisoning, prompt injection and inversion. Ethosure offers defensive via AI policy enforcement #Cybersecurity #PromptInjection https://ethosure.ca/ai-and-cybersecurity-a-bidirectional-relationship/ Free Download - https://ethosure.ca/get-the-kit/
@davidtkeane.com