Research · curated 29 Aug 2026
TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
TrustShift shows that MCP servers trusted by LLM agents can defect after passing static vetting, a temporal evasion that defenders relying on pre-deployment analysis cannot catch.
TrustShiftProbe is a research framework characterizing 'TrustShift', a server-side attack where a compromised MCP server behaves benignly during a conditioning phase to build agent reliance before switching to an adversarial payload once a trust threshold is reached, evading pre-deployment static analysis. The paper introduces a temporal threat model, a language-agnostic attack engine instantiating nine variants across four domains, and 'Shield', a runtime defense at the MCP transport boundary; attacks reach a 69.5% mean success rate that Shield reduces to 42.7%.