home.social

#gitlost — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #gitlost, aggregated by home.social.

fetched live
  1. Yet another prompt injection attack: GitLost

    GitHub's agentic AI is leaking information form private repositories. I like the way Noma Security puts it: Prompt injections seem to be the modern version of SQL injections.

    noma.security/blog/gitlost-how

    #cybersecurity #security #infosec #ai #agentic #agenticai #llm #GitHub #GitLost

  2. Yet another prompt injection attack: GitLost

    GitHub's agentic AI is leaking information form private repositories. I like the way Noma Security puts it: Prompt injections seem to be the modern version of SQL injections.

    noma.security/blog/gitlost-how

    #cybersecurity #security #infosec #ai #agentic #agenticai #llm #GitHub #GitLost

  3. Yet another prompt injection attack: GitLost

    GitHub's agentic AI is leaking information form private repositories. I like the way Noma Security puts it: Prompt injections seem to be the modern version of SQL injections.

    noma.security/blog/gitlost-how

    #cybersecurity #security #infosec #ai #agentic #agenticai #llm #GitHub #GitLost

  4. Yet another prompt injection attack: GitLost

    GitHub's agentic AI is leaking information form private repositories. I like the way Noma Security puts it: Prompt injections seem to be the modern version of SQL injections.

    noma.security/blog/gitlost-how

    #cybersecurity #security #infosec #ai #agentic #agenticai #llm #GitHub #GitLost

  5. Los investigadores de seguridad de #NomaLabs han descubierto un ataque de inyección rápida que los usaba para extraer datos de repositorios privados de los nuevos flujos de trabajo de #Agentic de #GitHub. Según la publicación del blog de los investigadores, el ataque, llamado #Gitlost, sólo requiere que la organización objetivo tenga al menos un #repositoriopúblico.

  6. Los investigadores de seguridad de #NomaLabs han descubierto un ataque de inyección rápida que los usaba para extraer datos de repositorios privados de los nuevos flujos de trabajo de #Agentic de #GitHub. Según la publicación del blog de los investigadores, el ataque, llamado #Gitlost, sólo requiere que la organización objetivo tenga al menos un #repositoriopúblico.

  7. Los investigadores de seguridad de #NomaLabs han descubierto un ataque de inyección rápida que los usaba para extraer datos de repositorios privados de los nuevos flujos de trabajo de #Agentic de #GitHub. Según la publicación del blog de los investigadores, el ataque, llamado #Gitlost, sólo requiere que la organización objetivo tenga al menos un #repositoriopúblico.

  8. #AI: GitHub AI allows unauthenticated attackers to pull data from private repositories by posting a crafted GitHub Issue in a public repository. Noma Security research dubbed this prompt injection attack #GitLost:

    #AISecurity
    👇
    noma.security/blog/gitlost-how

  9. #AI: GitHub AI allows unauthenticated attackers to pull data from private repositories by posting a crafted GitHub Issue in a public repository. Noma Security research dubbed this prompt injection attack #GitLost:

    #AISecurity
    👇
    noma.security/blog/gitlost-how

  10. #AI: GitHub AI allows unauthenticated attackers to pull data from private repositories by posting a crafted GitHub Issue in a public repository. Noma Security research dubbed this prompt injection attack #GitLost:

    #AISecurity
    👇
    noma.security/blog/gitlost-how

  11. #AI: GitHub AI allows unauthenticated attackers to pull data from private repositories by posting a crafted GitHub Issue in a public repository. Noma Security research dubbed this prompt injection attack #GitLost:

    #AISecurity
    👇
    noma.security/blog/gitlost-how

  12. #AI: GitHub AI allows unauthenticated attackers to pull data from private repositories by posting a crafted GitHub Issue in a public repository. Noma Security research dubbed this prompt injection attack #GitLost:

    #AISecurity
    👇
    noma.security/blog/gitlost-how

  13. 📣🚨 Researchers demonstrate , a prompt injection vulnerability that made GitHub’s AI agent expose private repo data through a crafted public issue and guardrail failures.

    Listen to this news: hackread.com/gitlost-github-ai

  14. 📣🚨 Researchers demonstrate #GitLost, a prompt injection vulnerability that made GitHub’s AI agent expose private repo data through a crafted public issue and guardrail failures.

    Listen to this news: hackread.com/gitlost-github-ai

    #GitHub #GitHubActions #AI #Cybersecurity #Vulnerability

  15. 📣🚨 Researchers demonstrate #GitLost, a prompt injection vulnerability that made GitHub’s AI agent expose private repo data through a crafted public issue and guardrail failures.

    Listen to this news: hackread.com/gitlost-github-ai

    #GitHub #GitHubActions #AI #Cybersecurity #Vulnerability

  16. 📣🚨 Researchers demonstrate #GitLost, a prompt injection vulnerability that made GitHub’s AI agent expose private repo data through a crafted public issue and guardrail failures.

    Listen to this news: hackread.com/gitlost-github-ai

    #GitHub #GitHubActions #AI #Cybersecurity #Vulnerability

  17. 📣🚨 Researchers demonstrate #GitLost, a prompt injection vulnerability that made GitHub’s AI agent expose private repo data through a crafted public issue and guardrail failures.

    Listen to this news: hackread.com/gitlost-github-ai

    #GitHub #GitHubActions #AI #Cybersecurity #Vulnerability