Ian Campbell<p>A little too much marketing copy in some places but it’ll be interesting to dive into the actual research. The specific scenarios involved exploiting gaps created by heterogeneous AI tool environments, like enterprises picking up this or that SaaS AI, without understanding (or without security having the political or person capital to control) the ad hoc agentic ecosystems that result.</p><p><a href="https://masto.deoan.org/tags/infosec" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>infosec</span></a> <a href="https://masto.deoan.org/tags/cybersecurity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cybersecurity</span></a> <a href="https://masto.deoan.org/tags/genai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>genai</span></a></p><p><a href="https://www.straiker.ai/blog/the-silent-exfiltration-zero-click-agentic-ai-hack-that-can-leak-your-google-drive-with-one-email" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">straiker.ai/blog/the-silent-ex</span><span class="invisible">filtration-zero-click-agentic-ai-hack-that-can-leak-your-google-drive-with-one-email</span></a></p>