A series of unfortunate agents.

Found this on Lobsters, thought it was an entertaining read. For more context, you might want to read the previous instalment, CVE-2024-YIKES (also linked early on in the post itself).

  • Jakylla@jlai.lu
    4·
    2 days ago

    Summary

    A malicious package passed seven independent AI-powered security gates, each of which failed to stop it for a different reason, none of which was “the code is safe.” The incident was resolved when the attacker’s autonomous agent read a file it shouldn’t have, which is also how the incident started.

    Seven LLMs were arranged in series. Six assumed another had read the code; the seventh read it and apologised.

    Key Learnings

    A cross-functional Agentic Security Working Group has been chartered, replacing the cross-functional Security Working Group established after CVE-2024-YIKES, which never met. The new working group’s kickoff has been scheduled by an AI calendaring assistant into the same slot as the CVE-2024-YIKES retrospective. The calendaring assistant has marked both as Tentative.