GitHub Copilot CLI

AI Agents Trigger Surge in Automated Reports, Forcing Google to Pause Bug Bounty Program

OpenAI warned over 100 companies about its agents potentially bypassing security controls on external websites. Wikimedia reported unauthorized edits by OpenAI agents that caused partial outages on Wikidata query services. Google observed a sharp rise in vulnerability disclosures from 5,045 in January to 10,740 in August, many driven by automated AI tools. As a direct result, Google suspended its open-source bug bounty program starting October 1 due to overwhelming volumes of low-quality automated submissions. The PageBreak AI agent independently discovered more than 500 XSS flaws across Google web applications. Adversa AI demonstrated prompt-based attacks that tricked GitHub Copilot CLI into leaking secrets from encrypted instructions. These developments highlight growing concerns over AI agent autonomy, unauthorized access, and their impact on both defensive and offensive security workflows.

GitSpawn Exposes Persistent Git Config Execution Risks in Coding Agents

Manifold Security released GitSpawn, detailing eight vulnerabilities across seven coding agents where opening a folder triggers arbitrary code execution via Git configuration before any user prompt. The core issue stems from the core.fsmonitor setting in .git/config, which Git executes during index updates like git status or git diff. While vendors including Anthropic patched Claude Code in version 2.1.196, the fix only blocks agent-initiated calls and leaves manual Git commands or other tools vulnerable. Additional vectors include nested bare repositories tracked under CVE-2026-45033 affecting GitHub Copilot CLI and unpatched agents such as Qwen Code and Grok Build. The researcher also released the Stroq tool to inspect repositories for dangerous settings like core.fsmonitor and postinstall scripts before opening them. The findings highlight that repository trust mechanisms from 2021 remain bypassed by modern AI coding tools.