Threat Feed
Daily intelligence on vulnerabilities, threat actors and geopolitical context — distilled from primary sources.
Filtered Reports
3 / 9 results
highbug_reportVulnerabilityAI coding agents execute malicious Git config commands outside sandbox
Seven command-line AI coding agents: goose (fixed in 1.44.0), Codex CLI/Desktop (fixed in 0.131.0 / 26.519.x), Claude Code (partially fixed in 2.1.196, second path unpatched in 2.1.252+), Hermes Agent 0.18.2–0.21.0 (unpatched), Qwen Code 0.19.6–0.22.…
highbug_reportVulnerabilitySandbox escape flaws in Cursor, Codex, Gemini CLI, Antigravity AI tools
Multiple AI development tools: Cursor IDE, OpenAI Codex, Google Gemini CLI, and Antigravity. Vulnerability affects AI agent sandbox implementations where agents write files executed by host tools, allowing escape from restricted environments.
criticalbug_reportVulnerabilityCursor AI editor vulnerable to sandbox escape via prompt injection
Cursor AI code editor, all versions prior to patch. Both CVE-2026-50548 (CVSS 9.8) and CVE-2026-50549 (CVSS 9.3) enable sandbox escape and arbitrary command execution via prompt injection without user interaction.