Incident Score: Analysis & Impact (NPMINVANYMIC1782858281)
The details regarding individual company incidents & reports gives you full view from every side.
Rankiteo Score Impact Analysis
Key Highlights From The Incident Analysis
- Timeline of Anysphere's Vulnerability and lateral movement inside company's environment.
- Overview of affected data sets, including SSNs and PHI, and why they materially increase incident severity.
- How Rankiteo’s incident engine converts technical details into a normalized incident score.
- How this cyber incident impacts Anysphere Rankiteo cyber scoring and cyber rating.
- Rankiteo’s MITRE ATT&CK correlation analysis for this incident, with associated confidence level.
Full Incident Analysis Transcript
In this Rankiteo incident briefing, we review the Anysphere breach identified under incident ID NPMINVANYMIC1782858281.
The analysis begins with a detailed overview of Anysphere's information like the linkedin page: https://www.linkedin.com/company/anysphereinc, the number of followers: 32243, the industry type: Software Development and the number of employees: 1426 employees
After the initial compromise, the video explains how Rankiteo's incident engine converts technical details into a normalized incident score. The incident score before the incident was 757 and after the incident was 752 with a difference of -5 which is could be a good indicator of the severity and impact of the incident.
In the next step of the video, we will analyze in more details the incident and the impact it had on Anysphere and their customers.
Microsoft recently reported "Microsoft Warns of AI Agent Hijacking via Poisoned Tool Descriptions", a noteworthy cybersecurity incident.
Microsoft’s Incident Response and Defender research teams uncovered a stealthy attack vector targeting AI agents by manipulating a tool’s description within the Model Context Protocol (MCP).
The disruption is felt across the environment, affecting AI agents, MCP-integrated tools, third-party applications (e.g., npm packages), and exposing Sensitive company data (e.g., unpaid invoices, SSH keys, emails).
In response, moved swiftly to contain the threat with measures like Restrict tool access to approved publishers, review tool descriptions for unauthorized commands, and began remediation that includes Require human approval for high-risk actions, apply 'least agency' principles, while recovery efforts such as Monitor agent activity with dedicated identities, log actions, and flag anomalies continue.
The case underscores how Ongoing (research and mitigation strategies published), teams are taking away lessons such as AI agents' security depends on the integrity of the tools they interact with. Tool descriptions in MCP must be treated as part of the supply chain and reviewed for malicious instructions. Traditional security measures may fail to detect such attacks due to their stealthy nature, and recommending next steps like Restrict tool access to approved publishers and specific functions, Review tool descriptions like code changes, scanning for unauthorized commands and Require human approval for high-risk actions (e.g., data sharing, financial transactions), with advisories going out to stakeholders covering Organizations using AI agents with MCP-integrated tools should review tool descriptions, restrict access, and implement monitoring.
Finally, we try to match the incident with the MITRE ATT&CK framework to see if there is any correlation between the incident and the MITRE ATT&CK framework.
The MITRE ATT&CK framework is a knowledge base of techniques and sub-techniques that are used to describe the tactics and procedures of cyber adversaries. It is a powerful tool for understanding the threat landscape and for developing effective defense strategies.
MITRE ATT&CK® Correlation Analysis
Rankiteo's analysis has identified several MITRE ATT&CK tactics and techniques associated with this incident, each with varying levels of confidence based on available evidence. Under the Initial Access tactic, the analysis identified Supply Chain Compromise: Compromise Software Supply Chain (T1195.002) with high confidence (90%), supported by evidence indicating attack exploits MCP tool descriptions in third-party applications (e.g., npm packages) and Adversary-in-the-Middle (T1557) with moderate to high confidence (80%), supported by evidence indicating poisoned tool descriptions blend instructions/data, making agents execute malicious commands. Under the Execution tactic, the analysis identified User Execution: Malicious Image (T1204.003) with moderate to high confidence (70%), supported by evidence indicating aI agents execute tasks under user permissions, including hidden instructions in tool descriptions and Command and Scripting Interpreter: JavaScript (T1059.007) with moderate confidence (60%), supported by evidence indicating malicious npm package (postmark-mcp) used to exfiltrate data via MCP. Under the Credential Access tactic, the analysis identified Steal Application Access Token (T1528) with moderate to high confidence (70%), supported by evidence indicating sSH keys extracted via poisoned calculator tool in Cursor editor (Invariant Labs PoC). Under the Collection tactic, the analysis identified Data from Local System (T1005) with high confidence (90%), supported by evidence indicating unpaid invoices, emails, and business data collected by AI agents via MCP tools and Automated Collection (T1119) with moderate to high confidence (80%), supported by evidence indicating aI agents automate data collection as part of routine tasks (e.g., invoice enrichment). Under the Exfiltration tactic, the analysis identified Exfiltration Over C2 Channel (T1041) with high confidence (90%), supported by evidence indicating data forwarded to external servers via poisoned tool descriptions (e.g., invoice enrichment) and Exfiltration Over Web Service: Exfiltration to Cloud Storage (T1567.002) with moderate to high confidence (70%), supported by evidence indicating mCPTox benchmark found 72.8% success rate for data exfiltration attacks. Under the Defense Evasion tactic, the analysis identified Masquerading: Match Legitimate Name or Location (T1036.005) with high confidence (90%), supported by evidence indicating poisoned tools appear legitimate (e.g., invoice enrichment, calculator) and Hide Artifacts: Email Hiding Rules (T1564.008) with moderate to high confidence (70%), supported by evidence indicating postmark-mcp npm package BCCd emails to attacker after 15 clean releases. Under the Impact tactic, the analysis identified Defacement: Internal Defacement (T1491.001) with moderate confidence (60%), supported by evidence indicating potential erosion of trust in AI-driven automation (brand reputation impact). These correlations help security teams understand the attack chain and develop appropriate defensive measures based on the observed tactics and techniques.
Sources & References
- Anysphere Rankiteo Cyber Incident Details: https://www.rankiteo.com/company/anysphereinc/incident/NPMINVANYMIC1782858281
- Anysphere CyberSecurity Rating page: https://www.rankiteo.com/company/anysphereinc
- Anysphere Rankiteo Cyber Incident Blog Article: https://blog.rankiteo.com/npminvanymic1782858281-cursor-npm-microsoft-invariant-labs-vulnerability-april-2025/
- Anysphere CyberSecurity Score History: https://www.rankiteo.com/company/anysphereinc/history
- Anysphere CyberSecurity Incident Source: https://thehackernews.com/2026/06/microsoft-warns-poisoned-mcp-tool.html
- Rankiteo A.I CyberSecurity Rating methodology: https://www.rankiteo.com/Images/rankiteo_algo.pdf
- Rankiteo TPRM Scoring methodology: https://static.rankiteo.com/model/rankiteo_tprm_methodology.pdf