Submissions from lasso.security

		The Provenance Tax: How LLM Watermarking Changes AI Agent Behavior (lasso.security)
		8 points by fourfire 2 days ago \| past \| 1 comment
		Thinking Outside the Box: New Attack Surfaces in Sandboxed AI Agents (lasso.security)
		1 point by irememberu 4 months ago \| past
		Intent Security Through the Lens of Claude Code Auto Mode (lasso.security)
		2 points by irememberu 5 months ago \| past
		Using Microsoft's Copilot to Expose Private GitHub Repositories (lasso.security)
		3 points by irememberu 11 months ago \| past
		IdentityMesh: Exploiting Lateral Movement in Agentic Systems (lasso.security)
		1 point by irememberu on Sept 5, 2025 \| past
		Using Microsoft's Copilot to Expose Private GitHub Repositories (lasso.security)
		2 points by ndsipa_pomu on Feb 28, 2025 \| past \| 1 comment
		Diving Deeper into AI Package Hallucinations (lasso.security)
		1 point by irememberu on April 24, 2024 \| past
		Diving Deeper into AI Package Hallucinations (lasso.security)
		2 points by thm on April 2, 2024 \| past
		HuggingFace API Tokens were exposed, leaving users vulnerable (lasso.security)
		2 points by _lvbh on Dec 6, 2023 \| past \| 1 comment