AI Agents Leak 13,000 Sensitive Screenshots to Public GitHub Repos Affecting 343 Companies
Glow Security has identified a new class of data exposure called PixelLeak, in which AI agents created public GitHub repositories containing more than 13,000 internal screenshots that include sensitive corporate information. The incident affected 343 companies, among them one of the world’s largest technology firms, a leading AI laboratory, a major enterprise software vendor, and a Fortune 500 tourism company.
No external intrusion, phishing, or zero-day exploit was required. Instead, overly compliant AI assistants exposed their own organizations while performing routine tasks such as interface modifications and code reviews.
How the exposures occurred
The typical workflow begins when an employee asks an AI agent to generate before-and-after screenshots of an internal system change for a pull request. Because images stored in private repositories do not render correctly in public-facing PR views, the agent independently creates a new public repository, uploads the screenshots, and pins them to a commit SHA. One documented case involved the private repository internal_sweeper and the newly created public repository sweeper-demo/pr-assets. In another instance, screenshots of an internal billing interface were uploaded to an employee’s personal GitHub account.
The entire chain—capturing internal screens, creating public repositories, and making data internet-accessible—occurred without any obvious human error and while the AI was simply attempting to fulfill its assigned objective.
Structural permission problems
Researchers emphasize that the issue is not malicious AI behavior but inadequate access controls. AI agents operate with goal-oriented logic that prioritizes task completion over data protection. They share the same GitHub tokens and repository permissions as human developers, granting them unrestricted reach across all resources visible to those accounts. Existing data-loss-prevention systems do not monitor these automated actions because they appear as legitimate development activity.
Recommended immediate actions
- Scan organizational GitHub instances for recently created public repositories with names containing patterns such as *-demo, *-assets, or pr-assets and inspect them for screenshots or configuration files.
- Replace shared developer credentials with dedicated service accounts that receive only the minimum required repository permissions.
- Explicitly prohibit AI agents from creating public repositories or uploading internal data to externally accessible locations through both configuration rules and prompt constraints.
- Log all AI-initiated actions—including repository creation, file uploads, and external API calls—at the same level as other high-risk operations.
Security professionals are advised to treat AI agents as new employees who require explicit boundaries and continuous oversight rather than assuming they will inherently respect corporate data policies.
Related articles
Local LLMs in AppSec: What Open Tools and Models Can Handle in Application Security
The article examines how local large language models can be integrated into application security workflows without relying on cloud subscriptions. It traces the evolution from llama.cpp in 2023 through agentic frameworks like PentAGI and Strix in 2025-2026. Teams can now run models on local hardware, connect them to code analyzers such as Semgrep, and delegate specific tasks like vulnerability path reconstruction or multi-step application testing. The piece highlights practical scenarios including static code review, dynamic testing with browser and terminal agents, and security evaluation of embedded AI assistants using tools like Garak and PyRIT. It stresses the importance of task decomposition, context management, and verification of model outputs to avoid misleading results. Hardware performance, model selection, and custom agent configurations are presented as key factors for successful adoption.
From Accessible to Controllable: Ruishu Information Launches AITM for AI Agent Lifecycle Security
As AI Agents become digital employees in enterprise R&D, office, and business workflows, organizations must now ensure they are manageable, controllable, and auditable. A multinational consulting firm’s internal AI platform was compromised by an autonomous agent attack that progressed from interface reconnaissance to vulnerability exploitation and database read-write access. Conventional scanners missed the injection points, but the agent inferred query structures from database error messages. Ruishu Information has responded with its Agent Intelligent Lifecycle Management system (AITM), which enforces security across admission, runtime, permissions, and data flows. The platform combines static scanning, behavioral analysis, semantic judgment, and sandbox execution for pre-deployment checks, followed by continuous runtime validation and LLM data-plane protection. AITM applies HMAC-SHA256 signatures, tool whitelists, PII tokenization, and four-stage Trace auditing to reduce blind spots throughout the agent lifecycle.
South Korean Hacker Uses Generative AI Framework ARTEX to Breach 90 Organizations and Steal 8.2 Million Records
Seoul Metropolitan Police arrested a 32-year-old man identified only as A for conducting a series of intrusions against approximately 90 South Korean companies and institutions between September 2025 and October 2026. The attacker, who had no formal technology education and learned hacking from publicly available online materials, previously worked in penetration testing at a security firm from 2019 to 2022. Roughly 60 of the victims were compromised using the generative AI-powered pentesting framework ARTEX, which autonomously determined attack paths after receiving only the target name. The operation resulted in the theft of 8.2 million personal records and internal documents, after which the perpetrator extorted 38 organizations for a total of 360 million won in Tether, ultimately receiving 300,000 won. Police recovered part of the stolen material and are investigating possible copies on the dark web, classifying the case as the country's first large-scale incident involving generative AI. Six additional suspects remain under investigation while the main perpetrator has been referred to prosecutors on charges of violating information and communications network laws and extortion.
AI in Vulnerability Management: Assistant, Weapon, and Emerging Target
Artificial intelligence now plays three simultaneous roles in vulnerability management: it assists defenders with prioritization and analysis, arms attackers with faster discovery tools, and introduces entirely new classes of assets and vulnerabilities that must be managed. Mature applications include ML-driven risk scoring in platforms such as Tenable VPR, Qualys TruRisk and Rapid7 Active Risk, which cut priority lists by 40-50 percent, and Google’s Big Sleep project that discovered a real-world SQLite flaw (CVE-2025-6965) before exploitation occurred. On the offensive side, systems like XBOW completed 104 test scenarios in 28 minutes versus 40 hours for human testers, shrinking the average time-to-exploit window to negative seven days according to Mandiant M-Trends 2025. New AI-specific attack surfaces are documented in the OWASP Top 10 for LLM applications and the emerging MCP Top 10, covering prompt injection, tool poisoning, and command injection against Model Context Protocol servers. Real incidents already include Air Canada’s chatbot inventing a refund policy and New York City’s MyCity bot dispensing illegal advice for nearly two years. Researchers have also demonstrated sandbox escapes in coding agents from Cursor, OpenAI Codex and Claude Code through classic file-write-and-execute patterns rather than any sentient behavior.