Netcrook
#GhostApproval
GhostApproval Turns AI Coding Assistants Into a File-System Trap
A trust-boundary flaw in six code agents shows how a malicious repository can manipulate sandboxed tools, not by breaking the model, but by abusing path handling and approval design.
GhostApproval Turns AI Coding Tools Into Unwitting File Writers
A newly disclosed trust-boundary flaw shows how repository tricks can push coding assistants past their workspace limits, where a single bad write may become a serious host-level security problem.
GhostApproval Raises a Hard Question for AI Coding Tools: What Happens When Trust Is Only an Illusion?
Wiz has disclosed GhostApproval, an attack method that uses a decades-old technique to mislead AI coding assistants and test the limits of approval-based security on developer machines.
When AI Approvals Drift: GhostApproval and the Broken Promise of Workspace Safety
A symlink-based trick shows how agentic coding tools can be pushed beyond the directory a user thinks they approved.
When an AI Editor Trusts the Wrong Path, the Workspace Stops Being Safe
A symlink flaw pattern called GhostApproval shows how approval prompts in AI coding tools can be fooled into sending writes beyond the intended workspace boundary.