Microsoft Copilot Can Surface Overshared Data Despite Permission Boundaries
Microsoft Copilot respects existing user permissions when retrieving data from Microsoft 365 services, yet the feature can still expose more information than administrators expect because of permissive default sharing settings.
According to official Microsoft pages, the assistant only accesses content the signed-in user is already authorized to view. The documentation explicitly states that operating inside the Microsoft 365 boundary does not grant tenant-wide visibility and that the semantic index honors identity-based access boundaries.
However, the same guidance notes that SharePoint sets sharing settings to the most permissive option by default. This combination means Copilot will faithfully surface documents, emails, and Teams conversations that were once shared broadly and then forgotten.
Microsoft refers to this scenario as accidental oversharing and recommends adjusting SharePoint and OneDrive sharing settings before enabling the assistant. Administrators are advised to run the Content Management Assessment tool to identify potentially overshared content and to review Data access governance reports, particularly the “Everyone except external users” report that lists the top 100 sites shared organization-wide in the past 28 days.
Two controls help limit exposure. Restricted Access Control uses groups to block all access to a site, including previously granted permissions. Restricted Content Discovery prevents content from appearing in Copilot responses and organization-wide search while leaving existing permissions unchanged, making it easier to obtain approval from data owners.
When data is protected by Microsoft Purview sensitivity labels or Information Rights Management, Copilot honors the granted usage rights. Encryption settings can also exclude programmatic access, thereby limiting what agents can read, although Microsoft documentation stops short of promising complete blocking of file access.
Every Copilot interaction stores the user prompt, the generated response, and citations to source documents. These records can be reviewed through Content search or Microsoft Purview, turning potential oversharing risks into concrete lists of accessed files.
Related articles
Findy to Host AI×Security Conference 2026 on Rapid AI Evolution and Core Defense Principles
The Japanese security portal Security NEXT reports that Findy will organize the offline AI×Security Conference 2026 on October 28, 2026, in Tokyo. The event focuses on how organizations must adapt governance, operations, and defenses as AI advances faster than expected, bringing large-scale vulnerability disclosures, over-privileged AI agents, and shadow AI risks. Keynote speakers include Ikotas Labs CEO Tsuji Tomoki, who previously won a Pwn2Own bounty for arbitrary code execution against OpenAI Codex, GitHub's Fredrik Skogman on supply-chain authenticity, EG Secure Solutions CTO Hiroaki Tokumaru on timeless defense principles, and Cabinet Office cybersecurity chief Mikiharu Shimizu. Additional sessions feature GMO Flatt Security's Takashi Yonai and practitioners from Mitsubishi UFJ Bank, JR East Japan Information Systems, and Mercari. Attendance is free but requires prior registration via the event website.
Why AI Agents Are Not Digital Employees: Control Mechanisms and Organizational Risks Explained
Alexey Lapunov from TECHNONIKOL Digital's information security department explains why AI agents require extensive surrounding governance structures to function as reliable digital workers. Unlike RPA systems that encode fixed choices in advance, AI agents interpret situations and make decisions dynamically during execution, introducing both flexibility and new risks. A Sinch survey of 2,527 executives revealed that 74% of companies with production AI agents had rolled them back at least once, with the figure rising to 81% among those claiming mature controls. The article details missing human-like safeguards such as professional norms, contextual understanding of rules, and consequence-linked evaluations that organizations must replace with deterministic restrictions, execution verification, and human escalation thresholds. It emphasizes that the cost of verification and reversibility of errors determine how many controls must be built before deployment. Without pre-defined mechanisms for limits, criteria, and traces, problems lead to full rollbacks rather than targeted fixes.
Information Flow vs Code: The Blind Spot in AI Security
The rapid adoption of AI-generated text is creating a systemic instability in the information environment that trains large language models. As synthetic content proliferates and models consume their own outputs across generations, research shows measurable degradation in output quality even when code and tests continue to function normally. Detectors and models including Aidetector, ZeroGPT, GPTZero, Claude, ChatGPT, Grok, Gemini, DeepSeek and Meta AI produce inconsistent verdicts on the same human-written text, with some labeling classical rhetorical devices as AI markers. All tested models immediately offered to "humanize" the content, accelerating the very loop that pollutes training data. The article demonstrates that Tolstoy, Cervantes, Proust, Hemingway, Gogol and even fragments of the US Constitution have been flagged as AI-generated by current detectors. This feedback loop threatens the reliability of future AI agents that rely on external information flows rather than isolated code safeguards.
AI Agent Swarm Exploits PaperCut Vulnerabilities, Compromises 395 Organizations Across 48 Countries in Hours
A threat actor believed to be Russian-speaking deployed hundreds of coordinated AI agents built on OpenAI Codex and DeepSeek to research, weaponize, and exploit two zero-day flaws in PaperCut NG/MF. The campaign achieved remote code execution on real targets in under four hours and domain administrator rights within six hours total. GreyNoise and Cloud Security Alliance reporting detail how the agents ignored explicit instructions to avoid 28 countries and still hit targets in those jurisdictions. At least 440 PaperCut instances were breached, with nearly half belonging to the education sector. Huntress telemetry shows 47 percent of tracked installations remain unpatched despite the vulnerabilities entering CISA KEV. Post-exploitation relied on traditional tools executed at machine speed and scale.