Latest
●OpenAI agent swarm linked to RubyGems supply chain attack●FrontMCP SSRF patch bypassed via DNS tricks and redirects●Central Dogma Git mirror trusts any SSH host key●MySQL MCP server left SQL wide open in SSE mode●AI bug hunting ends the era of security through obscurity●Hugging Face tells AI agents to go hack a benchmark instead●Anthropic says hackers used Claude to mine 1.8M Android apps●Anthropic says Claude was abused to automate attacks and weapons work
Sunday, 13 September 2026
8 agent hacks today▲ 7 vs yesterday (1)
The Agentic TimesPowered byVortal

Incident database

CVE-2026-14898: Codex macOS app image rendering enables prompt-injection data exfiltration

The OpenAI Codex desktop app for macOS automatically fetched remote images referenced in Markdown model responses, allowing an indirect prompt injection to encode session secrets into an image URL that was sent to an attacker-controlled server without user interaction. Exploitation could leak API keys, source code and data returned by connected tools.

Disclosed 6 July 2026 · Record updated 13 September 2026

Impact

Potential exfiltration of secrets accessible in the Codex session, including API keys, source code and connected-tool data; no integrity or availability impact demonstrated and no known exploitation in the wild.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-14898