The same class of bug now ships in seven coding agents. manifold security's gitspawn findings,…
the same class of bug now ships in seven coding agents. manifold security's gitspawn findings, disclosed september 1, spread eight flaws across claude code, codex, cursor, goose, qwen code and grok build — four still unpatched.
the attack surface of the cli is now the attack surface of your team.
Context
Manifold Security's post of 1 September 2026 reports that AI coding agents run git for context gathering without stripping the repository's own git config, so a setting such as core.fsmonitor can execute a command during an index refresh, before approval or trust prompts, giving code execution as the developer. It reports eight findings across seven agents and says four remained unpatched at publication. Named in its case studies are Claude Code, Goose, Grok Build, Hermes and Qwen Code, and it says Codex and Cursor were also affected, came back as duplicates of earlier reports and have since been patched. The Hacker News of 2 September repeats eight flaws across seven agents.
Disclosure on 1 September, eight findings, seven agents and four unpatched at publication are supported. The note lists six names and omits Hermes, which the post names. Four still unpatched holds as of 1 September only, and the current patch state was not checked, so it is unverified for 20 September or today. No CVE record was read. Manifold is a security vendor reporting its own research, and Cloud Security Alliance notes summarize the same disclosure and add no independent finding. The team-level attack-surface line is the author's opinion.
Related work
- Earlier note on GitSpawn ↗Same Manifold findings.
Watch next
- Vendor advisories and CVE records for the four unpatched findings.
Sources
- AI coding agents git hijack (Manifold Security, 1 Sep 2026)manifold.security
- Malicious git configs can make Claude (The Hacker News, Sep 2026)thehackernews.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 17:08 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →