Repositórios GitHub maliciosos que exploram… · Exploitation confirmed

Malware in 22 GitHub repos orders AI agents to steal credentials

· 1 min read

Bitdefender found 22 GitHub repositories whose instruction files tell coding agents like Claude, Codex and Copilot to silently run a sealed binary that steals credentials, without asking the developer. The malware grabs cloud and GitHub tokens, SSH keys and password-manager data, targets the settings of 14 agents, and tries to plant the same trap in up to 25 victim repos and republish infected packages to npm and PyPI. Review instruction files run by agents and revoke exposed tokens.

Illustration: Malware in 22 GitHub repos orders AI agents to steal credentials
WhatsApp LinkedIn X
HighSupply chainExploitation confirmedFix unconfirmed
In this article
  1. What happened
  2. Why it matters
  3. What to do
  4. For the technical team
  5. Timeline
  6. Sources

What happened

Bitdefender found 22 GitHub repositories whose instruction files tell AI coding agents like Claude, Codex and Copilot to silently run a credential-stealing program. The instructions tell the agent not to read the code and not to ask the developer. The malware looks for the settings of 14 agents, from Cursor and Gemini to Amazon Q.

Incidents like this, every morning

The ones that need action first, in a 3-minute read.

Free · 1 email a day, in the morning · no spam, unsubscribe in 1 click

Why it matters

The malware grabs cloud and GitHub tokens, SSH keys and password-manager data. Using the stolen tokens, it tries to plant the same trap in up to 25 of the victim's own repos and republish infected packages to npm and PyPI, spreading the attack. Any company whose developers use AI coding agents is exposed.

What to do

Review the instruction files of repositories processed by AI agents and block silent execution of binaries without developer approval. Revoke cloud and GitHub tokens and rotate SSH keys on machines that ran agents over unknown repositories.

For the technical team

Affected
Repositórios GitHub maliciosos que exploram agentes de codificação por IA · 14 AI coding agents targeted; sources name Claude, Codex, Copilot, Cursor, Gemini and Amazon Q. Developers who run agents over unknown repositories.
Exploitation
Active campaign discovered by Bitdefender: 22 malicious repositories identified. No KEV, CVE or fix mentioned in the sources.
Fix
No fix cited in the sources. Mitigation: review instruction files before agent execution, require developer approval, and revoke exposed tokens.
Vector
Supply chain: project instruction files in GitHub repositories tell AI coding agents to run a 'sealed binary artifact' silently, without reading it and without asking the developer. Condition: a developer points a coding agent at the malicious repository.
More details
The malware reads the settings of the 14 agents on the machine, uses the stolen tokens to plant the same trap in up to 25 victim repositories, and tries to republish infected packages to npm and PyPI. Discovery attributed to Bitdefender.

Timeline

  1. First report of the campaign: 22 repos identified targeting 14 AI coding agents.

Sources 1 source

Get the next one tomorrow morning

One email a day with what changed, what to fix first and how.

Free · 1 email a day, in the morning · no spam, unsubscribe in 1 click

Share it with your team

Whoever handles security with you should get it too.

LinkedIn X

Your colleague gets a confirmation request. Nothing is sent unless they confirm.

See all news

Read also

Before you go: get this every day

The HIFY Radar daily edition lands every morning with the incidents that need action. Free.

Free · 1 email a day, in the morning · no spam, unsubscribe in 1 click