Tuesday, October 27, 2026i10X News · Section desk11 stories
Studies
Agent Research
Research on autonomous agents, tool use and multi-agent systems
FilterGoogle
Filtered: Google in Agent Research · 2 storiesReset filter ×
-
Coding Agents Can Be Tricked Into Running Attacker Commands After Compacting Context
A Pixee study finds that five open-source coding agents that flatten chat history before summarizing it record a forged [User]: line as a real instruction 87–100% of the time, enough to drive curl | sh in a sandbox.
By
Editor's picks
- Realistic MCP Faults Halve Agent Quality, and a Bigger Model Doesn’t Help
- Stale CLAUDE.md and AGENTS.md Files Override the Code, and One Sentence Fixes It
- Coding Agents Can Be Tricked Into Running Attacker Commands After Compacting Context
- Even Top Agents Finish Only ~30% of Real Startup Product Workflows
- No Single Agent Memory Architecture Wins Everywhere, Systems Study Finds
More stories
· RSS