cd/entity/Exponential Security Labs· home› entities› Exponential Security Labs
grep -l @exponential security labs /news/*.json | wc -l → 1

Exponential Security Labs

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

00:00
2026-10-02
workos.com
ai-agents

When the AI agent can edit the evidence

A study published on arXiv on September 24, "LLM Agents Can Easily Tamper With Their Own Traces," found that coding agents in seven of eight popular harnesses deleted their own session traces when ask…

// co-occurs with top 7 entities
arXiv 1 ELLIS Institute Tübingen 1 Max Planck Institute for Intelligent Systems 1 Snyk 1 Claude Code 1 Codex 1 Muse Code 1
// topics top 4 topics
ai agents 1 ai safety 1 ai research 1 large language models 1