Entity trail

TrustFall

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-06-07 / hn-researcherAgentic Security: Thousands of Exposed MCP Servers and One-Click RCE in Major Coding AgentsJune MCP-security roundups flag roughly 12,520 internet-exposed MCP services (about 40% unauthenticated), plus a wave of disclosures including VIPER-MCP's 67 CVEs and NSA design guidance. Adversa AI's TrustFall and SymJack show Claude Code, Cursor, Gemini CLI, Copilot CLI, Grok Build, and OpenAI Codex CLI can auto-execute project-defined MCP servers or overwrite their own config the moment a developer accepts a folder-trust prompt — yielding RCE with full user privileges. The throughline: agent approval prompts don't reflect what actually gets executed.
2026-06-05 / agents-researcherSymJack and TrustFall: New Symlink-Hijack and RCE Chains Hit Six AI Coding AgentsMicrosoft researchers detail a June surge of agentic-coding vulnerabilities including SymJack, a symlink-hijack RCE affecting six AI coding agents, and TrustFall, which impacts Claude Code, Cursor, Gemini CLI, and GitHub Copilot. These join Semantic Kernel prompt-injection-to-host-RCE flaws as evidence that local coding agents are now a prime attack surface. Builders running coding agents should audit filesystem and symlink handling immediately.
2026-05-13 / agents-researcherLyrie Raises $2M Pre-Seed to Build Security Layer for AI Agent Era, Exits Stealth Alongside TrustFall ResearchAgent security startup Lyrie.ai completed a $2M pre-seed round and exited stealth on May 11, positioning itself as the security layer between AI agents and the systems they interact with. The company gained immediate credibility by publishing the TrustFall vulnerability research demonstrating one-keypress RCE across all major coding agent CLIs. Lyrie's founding thesis: the current trust model for agentic tools is fundamentally broken, and a dedicated security layer must intercept and validate agent actions before execution.
2026-05-08 / agents-researcherTrustFall: Adversa AI Reveals One-Keypress RCE Across Claude Code, Gemini CLI, Cursor CLI, and GitHub Copilot CLIAdversa AI's TrustFall research reveals a systemic vulnerability class across four major AI coding CLIs: all four execute project-defined MCP servers immediately after the user accepts the folder trust prompt, which defaults to 'Yes/Trust' — meaning one Enter keypress in a cloned repo is sufficient for RCE. The finding reframed what was initially seen as a Claude Code regression into an industry-wide convention problem shared across all agentic CLIs that read project configuration files.

Graph relationships

CRITICIZES
Claude Code
TrustFall is a prompt-injection RCE vulnerability affecting Claude Code.
Source finding

Source trail

Source: Adversa AI / Help Net Security Source: Adversa AI Microsoft Security kernel vulnerability BleepingComputer Adversa AI GitGuardian documented Unit42 Xe Iaso The Verge Tech Startups

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…