Storia in 5 fonti

GhostApproval bug breaks 6 top AI coding agents

Wiz's 'GhostApproval' uses an old symlink trick to make six AI coding agents, from Amazon Q to Cursor, write outside the sandbox and hand over the box.

Raccontata da

Confronto fonti

5 prospettive sulla stessa storia

AI · summaries

thenextweb.comStai leggendo1 mese fa

GhostApproval bug breaks 6 top AI coding agents

Wiz's 'GhostApproval' uses an old symlink trick to make six AI coding agents, from Amazon Q to Cursor, write outside the sandbox and hand over the box.

originale

Timeline cronologica

mercoledì 8 luglio 2026·theregister.com
Bug in top AI coding agents shows that Unix-era security headaches never really die
'GhostApproval' problem highlights human-in-the-loop fails
mercoledì 8 luglio 2026·thenextweb.com
GhostApproval bug breaks 6 top AI coding agents
Wiz's 'GhostApproval' uses an old symlink trick to make six AI coding agents, from Amazon Q to Cursor, write outside the sandbox and hand over the box.

thehackernews.com

1 mese fa

GhostApproval Symlink Flaws Could Let Malicious Repos Run Code in AI Coding Agents

Wiz says GhostApproval abuses symlinks so AI coding agents write to SSH keys or shell startup files while showing benign paths.

Leggi questa versione → originale

theregister.com1 mese fa

Bug in top AI coding agents shows that Unix-era security headaches never really die

'GhostApproval' problem highlights human-in-the-loop fails

Leggi questa versione → originale

securityweek.com1 mese fa

AI Coding Tools Tricked Into Hacking Developer Machine via Decades-Old Technique

Several AI coding assistants were tricked into facilitating developer machine hacking via an attack technique that has been known for decades.

Leggi questa versione → originale

infoworld.com1 mese fa

AI coding tool hole illustrates a big problem with human in the loop

The flaw, which impacted Amazon, Anthropic, Google, Cursor and others, let the agent give the human false information on which to make decisions.

Leggi questa versione → originale

giovedì 9 luglio 2026·

infoworld.com

AI coding tool hole illustrates a big problem with human in the loop

The flaw, which impacted Amazon, Anthropic, Google, Cursor and others, let the agent give the human false information on which to make decisions.

giovedì 9 luglio 2026·

thehackernews.com

GhostApproval Symlink Flaws Could Let Malicious Repos Run Code in AI Coding Agents

Wiz says GhostApproval abuses symlinks so AI coding agents write to SSH keys or shell startup files while showing benign paths.

giovedì 9 luglio 2026·

thehackernews.com

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

AI Now’s Friendly Fire PoC shows Claude Code and Codex running README-planted payloads on hosts when autonomous command approval is enabled.

giovedì 9 luglio 2026·

securityweek.com

AI Coding Tools Tricked Into Hacking Developer Machine via Decades-Old Technique

Several AI coding assistants were tricked into facilitating developer machine hacking via an attack technique that has been known for decades.