Tag: llm

All the articles with the tag "llm".

• Hermes Agent and the Search Provider Attack Surface

  28 Jun, 2026

  Hermes Agent's pluggable search provider architecture creates a layered attack surface most users don't see: prompt injection through search results, credential exfiltration via scheduled jobs, and silent query routing through third-party infrastructure.

• AI Agent Security: The Lethal Trifecta and the Rule of Two

  27 Jun, 2026

  Two complementary frameworks — Simon Willison's Lethal Trifecta and Meta's Rule of Two — explain why AI coding agents are reliably exploitable when they combine private data access, untrusted input, and external communication.