GitSpawn: Untrusted repos can execute code via AI coding agents

ffourfire 2 days ago 3 commentsRead Article on manifold.security

ZH version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

0% Positive

Analyzed from 94 words in the discussion.

Discussion (3 Comments)Read Original on HackerNews

grncdr•about 1 hour ago

> Git reads that setting from the repository's own .git/config. So a repository can ship this:

Followed by:

> Delivery is worth being precise about, because git never carries this. Cloning a hostile URL does nothing, and neither does fetch or pull.

AI slop nothing burger. The “exploit” has nothing to do with coding agents.

kadoban•36 minutes ago

> AI slop nothing burger. The “exploit” has nothing to do with coding agents.

It's pretty small potatoes, but it is a harness ~bug that they treat this so poorly. It getting triggered before some of them even ask you if you trust the directory is pretty bad.

DivingForGold•2 days ago

GitSpawn: A Single Flaw Let's Untrusted Repos Run Code in Claude Code, Codex, Cursor, and Grok