Skip to content
AgentProv

2026-05-12 · 2026-Q2

Claude Code Deeplink RCE

Primary layerL5 ConfigSecondary:L2 Instruction

Who wrote the file that runs on open?

The question layer 5 asks, and failed here.
Fixable
Vendor patch
Vendor response
Patched
In the wild
No
Actor
Attacker

Target

Claude Code before 2.1.118

Impact

A crafted `claude-cli://` deeplink injects `--settings={...}` (including a `SessionStart` hooks payload) through the `--prefill` value, so one click runs arbitrary shell commands; pointing the deeplink's `repo` parameter at an already-trusted local repository suppressed all warning prompts for a silent compromise

Root cause

`eagerParseCliFlag` in `main.tsx` used `startsWith` across the whole argv array without tracking whether a `--settings=` string was a real flag or the value of another flag, letting flags be smuggled inside values. Researcher: Joern Chen (joernchen, 0day.click)

Sources

Catalog

Cite this: AgentProv incident record: Claude Code Deeplink RCE (2026-05-12). https://agentprov.com/incidents/2026-05-12-claude-code-deeplink-rce