9d ago

Researchers disclosed two sandbox escapes in OpenAI Codex CLI and desktop app, including Heapjack. Opening an untrusted repo can yield unsandboxed host command execution, breaking agent containment. T

Researchers disclosed two sandbox escapes in OpenAI Codex CLI and desktop app, including Heapjack. Opening an untrusted repo can yield unsandboxed host command execution, breaking agent containment. Treat AI agents as untrusted execution and audit workflows. # HeapJack # CodexSecurity # SandboxEscape https:// cyberworldops.eu/en/openai-cod ex-sandbox-flaws-turn-repository-analysis-into-host-level

1 reportother

Claim audit

No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.

All coverage

Researchers disclosed two sandbox escapes in OpenAI Codex CLI and desktop app, including Heapjack. Opening an untrusted repo can yield unsandboxed host command execution, breaking agent containment. T

mastodon:infosec-exchangeother9d ago kagi ↗

Researchers disclosed two sandbox escapes in OpenAI Codex CLI and desktop app, including Heapjack. Opening an untrusted repo can yield unsandboxed host command execution, breaking agent containment. Treat AI agents as untrusted execution and audit workflows. # HeapJack # CodexSecurity # SandboxEscape https:// cyberworldops.eu/en/openai-cod ex-sandbox-flaws-turn-repository-analysis-into-host-level