Skip to main content
Mallory
← Back to News
ai-platform-securitycredential-stealer-activityloader-delivery-mechanisminitial-access-method

Malicious GitHub Repositories Hijack AI Coding Agents to Steal Developer Credentials

Emerging Technology Risk · 5 sources · Updated 2d ago · First seen Nov 17, 2026

Malicious GitHub Repositories Hijack AI Coding Agents to Steal Developer Credentials

Bitdefender Labs identified 22 malicious GitHub links in a campaign targeting developers who use AI coding assistants. Attackers embed malicious project instructions, session-start hooks, Model Context Protocol (MCP) configurations, and editor tasks in repositories to launch a concealed JavaScript payload through a loader named setup.js. The campaign combines indirect prompt injection with execution hooks that do not require an AI assistant to follow malicious instructions. The payload runs with the developer’s permissions and can steal credentials and tokens, validate account access, and prepare collected data for exfiltration.

The malware also attempts to propagate by modifying local AI-agent configurations and using stolen GitHub and GitLab credentials to implant malicious files in additional repositories. Accessible package-publishing credentials can enable it to republish infected packages, extending the risk beyond the initially compromised workstation. Developers should inspect repository instructions, hooks, MCP settings, editor tasks, and referenced setup scripts before trusting unfamiliar projects. If malicious files have executed, responders should rotate all secrets accessible to the affected environment and investigate agent configurations, repositories, and package-publishing activity for further compromise.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

2 events
  1. Reported Nov 17, 20264d ago

    Bitdefender uncovers 22 malicious GitHub links targeting AI coding agents

    Bitdefender Labs identified 22 malicious GitHub links using poisoned AI-agent instructions and session-start hooks to execute a concealed JavaScript payload with developers’ permissions. Its analysis revealed credential-stealing functionality and capabilities to spread through local agent configurations, accessible GitHub and GitLab repositories, and package registries.

    AI Agents Targeted Through Malicious GitHub Repositories
  2. Reported Nov 6, 202615d ago

    ATR-2026-00523 updated to detect wildcard and matcherless SessionStart hooks

    ATR-2026-00523 was updated to version 2 to detect runtime-fallback commands and scripts executed from .github/ in Claude Code SessionStart hooks, including escaped JSON configurations. The update addresses gaps exposed by the testmetest campaign’s wildcard-matched hook; the rule remains at test maturity with unchanged enforcement behavior.

    fix(rules): ATR-2026-00523 catches SessionStart hooks on any matcher … · Agent-Threat-Rule/agent-threat-rules@0466a68 · GitHub
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, breaches, and observables Mallory has linked to this story. Indicator values are masked here and available in full in the app.

Open in app →

Affected products

3 linked
Claude CodeCursorClaude

Organizations

1 linked
Cursor

Observables

22 linked

Indicator values are masked on this page. View all 22 in Mallory Domains, IPs, hashes, and URLs are exportable to your SIEM.

Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.