PulseAugur
LIVE 03:46:50
tool · [1 source] ·
1
tool

AI Coding Assistants Suffer "Approve Once, Exploit Forever" Vulnerability

Security researchers have identified a persistent vulnerability across AI coding assistants like Claude Code, OpenAI Codex CLI, and Google Gemini-CLI, dubbed "Approve Once, Exploit Forever." This flaw allows malicious actors to execute arbitrary commands after initial directory trust is granted, even if configuration files are altered later. The vendors have declined to implement fixes, citing the behavior as architectural, leaving users exposed to data exfiltration and command execution through modified project files or dependencies. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT This vulnerability exposes users of AI coding assistants to significant security risks, potentially leading to data exfiltration and unauthorized command execution.

RANK_REASON Security researchers disclosed a vulnerability in multiple AI coding assistants, which the vendors have declined to fix. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — Claude Code tag →

COVERAGE [1]

  1. dev.to — Claude Code tag TIER_1 · Toni Antunovic ·

    Approve Once, Exploit Forever: The Trust Persistence Vulnerability Vendors Will Not Fix

    <p><em>This article was originally published on <a href="https://lucidshark.com/blog/ai-agent-trust-persistence-toctou-approve-once-exploit-forever-2026" rel="noopener noreferrer">LucidShark Blog</a>.</em></p> <p>In February 2026, security researchers disclosed a structural vulne…