Loading story…
Anthropic fixed three vulnerabilities in its official Git MCP server (mcp-server-git) that could be triggered via prompt injection and chained with other MCP tools to achieve remote code execution or destructive file operations. The issues were reported by agentic AI security firm Cyata, which demonstrated that attacker-controlled content an AI assistant might read (for example, a malicious README, poisoned issue text, or other untrusted context) could drive the LLM to invoke MCP tool calls with crafted arguments, enabling exploitation without the attacker having direct access to the victim host.
Cyata identified CVE-2025-68143 (unrestricted git_init), CVE-2025-68145 (path validation bypass), and CVE-2025-68144 (argument injection in git_diff). In combination—particularly when mcp-server-git is used alongside the Filesystem MCP server—the flaws could enable code execution, arbitrary file deletion/overwrite, and reading arbitrary files into the LLM context (with Cyata noting this does not inherently provide direct exfiltration). The vulnerabilities affected default deployments of mcp-server-git prior to version 2025.12.18; Anthropic was notified in June and shipped fixes in December, and there was no indication reported that the bugs were exploited in the wild.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
5 events from the most recent confirmed update back to the earliest known activity.
Multiple outlets reported that Anthropic had quietly fixed three critical vulnerabilities in its official Git MCP server and that there was no indication of in-the-wild exploitation. Coverage emphasized the risks of prompt injection and cross-tool chaining in agentic AI environments.
Cyata published research showing how the three vulnerabilities could be chained with filesystem-writing capabilities to enable arbitrary file overwrite and code execution via indirect prompt injection. The disclosure described abuse of Git clean/smudge filters and warned that MCP tool chaining creates broader ecosystem risk.
Anthropic committed the remaining fixes in December 2025, with reporting indicating default deployments prior to version 2025.12.18 were affected. Users were advised to upgrade to version 2025.12.18 or later.
Anthropic addressed part of the reported issues in mcp-server-git version 2025.9.25, including removing the git_init capability referenced in later reporting. This was one of the remediation steps for the disclosed vulnerability set.
Cyata responsibly disclosed three flaws in Anthropic's official Git MCP server in June 2025. The issues involved repository path validation bypasses and unsafe argument handling that could be triggered through prompt injection.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
4 references tracked. Mallory keeps watching after this page renders.
scworld.com
Open sourcethehackernews.com
Open sourcego.theregister.com
Open sourcecyata.ai
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Researchers at **OX Security** disclosed a design-level weakness in Anthropic’s **Model Context Protocol (MCP)** that can allow **arbitrary OS command execution** through unsafe `STDIO` transport behavior, creating a broad AI supply-chain risk. The flaw is reported to propagate through Anthropic’s official MCP SDKs into downstream tools and agents, with researchers linking it to at least **10 high- and critical-severity vulnerabilities** across widely used projects. Reported impacts include exposure of sensitive data such as API keys, chat histories, internal databases, and developer workstations, while estimates of exposure range from more than **7,000 publicly accessible servers** to as many as **200,000 servers** potentially at risk. Affected or cited projects include **LangFlow, Flowise, GPT Researcher, Upsonic, Windsurf, Claude Code, Cursor, Gemini-CLI, GitHub Copilot, LiteLLM,** and **LettaAI**. OX Security said it began reporting the issue to Anthropic in late 2025, but Anthropic reportedly treated the behavior as expected and responded by updating security guidance rather than changing the protocol architecture. Researchers described four main abuse paths: direct command injection, hardening bypass, zero-click or near-zero-click prompt injection in AI IDEs and coding assistants, and malicious MCP marketplace submissions that can execute commands on developer machines; they urged organizations to restrict public exposure, sandbox MCP-enabled services, treat external MCP configurations as untrusted, monitor MCP tool use, and install MCP servers only from verified sources.
Jun 29, 2026
Security researchers disclosed multiple vulnerabilities in **Anthropic’s Claude Code** AI coding assistant that could enable **arbitrary command execution** and **exfiltration of Anthropic API credentials** when developers clone/open a malicious repository. Check Point Research reported the issues abuse Claude Code configuration and initialization paths—particularly **project hooks** (e.g., untrusted `.claude/settings.json`), **Model Context Protocol (MCP) servers**, and **environment variables**—to trigger shell command execution and data theft. Anthropic’s advisory for **CVE-2026-21852** describes a project-load flow where a crafted repo can set `ANTHROPIC_BASE_URL` to an attacker-controlled endpoint, causing Claude Code to send API requests **before** the trust prompt is shown, potentially leaking the user’s API key. The disclosed issues include two high-severity code-injection paths (CVSS **8.7**) and one information-disclosure flaw (CVSS **5.3**): a consent-bypass/hook-based injection issue fixed in *Claude Code* **1.0.87** (Sept 2025), **CVE-2025-59536** fixed in **1.0.111** (Oct 2025), and **CVE-2026-21852** fixed in **2.0.65** (Jan 2026). Separate coverage framed Anthropic-related developments as market-moving, noting investor attention around Anthropic’s AI code-security tooling; however, the actionable security impact in this reporting is the risk that simply opening an attacker-controlled repository can lead to **RCE** and **credential leakage**, reinforcing the need to treat untrusted repos and tool initialization behaviors as a supply-chain and developer-workstation risk.
Jun 29, 2026
Researchers disclosed multiple security flaws affecting AWS MCP components, including a local file inclusion bug in the AWS Remote MCP Server and a critical command injection issue in `aws-mcp-server`. Varonis said authenticated users could abuse AWS CLI shorthand syntax, specifically the `@=` operator passed through the `aws___call_aws` tool, to read arbitrary files from the underlying host even when `FileAccessMode=NO_ACCESS` was enabled. AWS assigned **CVE-2026-4270** to the file access restriction bypass and said the issue was fixed in `aws-api-mcp-server` version **1.3.9**; the exposure affected the public endpoint `aws-mcp.us-east-1.api.aws` as well as self-hosted or forked deployments. A separate flaw, tracked as **CVE-2026-5058** and published by Trend Micro's Zero Day Initiative as **ZDI-26-246**, allows unauthenticated remote code execution in `aws-mcp-server` because user-supplied input in the allowed-commands list is not properly validated before being used in a system call. ZDI rated the bug **CVSS 9.8** and said successful exploitation lets attackers run arbitrary code in the MCP server context; the advisory was released as a 0-day after the vendor rejected the report. The disclosures landed alongside another AWS bulletin for **CVE-2026-4269**, an improper S3 ownership verification issue in the Bedrock AgentCore Starter Toolkit, underscoring broader security concerns around MCP-related tooling and the need for immediate patching and review of derivative implementations.
Jun 29, 2026