CVE-2025-53773
GitHub Copilot and Visual Studio Remote Code Execution Vulnerability
Description
Improper neutralization of special elements used in a command ('command injection') in GitHub Copilot and Visual Studio allows an unauthorized attacker to execute code locally.
INFO
Published Date :
Aug. 12, 2025, 6:15 p.m.
Last Modified :
Aug. 15, 2025, 5:01 p.m.
Remotely Exploit :
No
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Update GitHub Copilot and Visual Studio.
- Review and sanitize all user inputs.
- Implement least privilege for operations.
Public PoC/Exploit Available at Github
CVE-2025-53773 has a 49 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2025-53773.
| URL | Resource |
|---|---|
| https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-53773 | Vendor Advisory |
| https://embracethered.com/blog/posts/2025/github-copilot-remote-code-execution-via-prompt-injection/ | Exploit Third Party Advisory |
| https://news.ycombinator.com/item?id=44883108 | Third Party Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2025-53773 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2025-53773
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Defensive detection for indirect prompt injection (IPI) in agentic LLM systems
Python
Indirect prompt injections (OWASP LLM01) SAST scanner
Dockerfile Shell Python
None
Dockerfile CSS HTML JavaScript
Dual-identity delegation-chain enforcement for OpenClaw and Hermes-style agents.
TypeScript JavaScript Go Python
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.
Shell
Benchmarking silent security failures in AI coding agents.
Python HTML
None
Python
AI agent security auditor. Scans MCP server configs across 7 attack categories with CVSS 3.1 scoring and OWASP Agentic Top 10 mapping.
Python
AI security skills grounded in mid-2026 threat reality, not stale framework documentation
agents-md ai-security ai-skills cisa-kev claude-code codex compliance cve d3fend dora eu-ai-act iso-27001 mitre-atlas nis2 nist security threat-intelligence rwep
Dockerfile JavaScript Shell Python
LLM Security Roadmap 2026: Türkiye'nin ilk kapsamlı Türkçe yapay zeka güvenlik yol haritası! Sıfırdan uzmanlığa; araçlar, CTF platformları, akademik makaleler ve pratik kaynaklar.
ai-red-teaming career-guide learning-path ai-security-roadmap llm-roadmap turkish-resources
AI Agent Security: Otonom yapay zeka ajanlarının ve MCP protokolünün güvenlik riskleri. Excessive Agency, tool poisoning ve Meta'nın "İki Kural" (Rule of Two) savunma çerçevesi.
agentic-ai ai-agents excessive-agency mcp-protocol model-context-protocol
Before you tweet your launch — run these 47 checks. Same patterns behind the Lovable RLS CVE (170 apps, March 2025) and the Moltbook leak (1.5M API tokens, Feb 2026).
ai-coding bolt claude-code cursor lovable mcp nextjs rls security supabase v0 vibe-coding
Helmet.js for AI Agents — Security middleware for production AI agents
Python
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.
agent-safety ai-agents ai-security claude-code claude-code-skill llm-security mcp mcp-security plugin prompt-injection skill vibe-coding bridgemind
Shell
Safety linter and regression gate for AI agents. Catches security regressions before deployment.
Python HTML
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2025-53773 vulnerability anywhere in the article.
-
TheCyberThrone
The Exploit That Arrived in an Email and Left With Your Data
The Distinction Nobody Makes Clearly EnoughWhen most practitioners hear “prompt injection,” they picture a user typing malicious instructions directly into a chatbot. “Ignore previous instructions. Re ... Read more
-
CybersecurityNews
Critical Vulnerabilities in GitHub Copilot, Gemini CLI, Claude, and Other Tools Impact Millions of Users
The software development landscape has been fundamentally altered by AI-driven integrated development environments (IDEs). Tools like GitHub Copilot, Gemini CLI, and Claude Code have evolved from simp ... Read more
-
CybersecurityNews
GitHub Copilot RCE Vulnerability via Prompt Injection Leads to Full System Compromise
A critical security vulnerability in GitHub Copilot and Visual Studio Code has been discovered that allows attackers to achieve remote code execution through prompt injection attacks, potentially lead ... Read more
-
BleepingComputer
Microsoft August 2025 Patch Tuesday fixes one zero-day, 107 flaws
Today is Microsoft's August 2025 Patch Tuesday, which includes security updates for 107 flaws, including one publicly disclosed zero-day vulnerability in Windows Kerberos.This Patch Tuesday also fixes ... Read more
-
CybersecurityNews
Microsoft Patch Tuesday August 2025 Released – 107 Vulnerabilities Fixed Including 36 RCE
Microsoft released its August Patch Tuesday security updates, addressing a total of 107 vulnerabilities across its product ecosystem. The update includes fixes for 90 vulnerabilities, classified as fo ... Read more
The following table lists the changes that have been made to the
CVE-2025-53773 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Aug. 15, 2025
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:microsoft:visual_studio_2022:*:*:*:*:*:*:*:* versions from (including) 17.14.0 up to (excluding) 17.14.12 Added Reference Type Microsoft Corporation: https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-53773 Types: Vendor Advisory Added Reference Type CVE: https://news.ycombinator.com/item?id=44883108 Types: Third Party Advisory Added Reference Type CVE: https://embracethered.com/blog/posts/2025/github-copilot-remote-code-execution-via-prompt-injection/ Types: Exploit, Third Party Advisory -
CVE Modified by af854a3a-2127-422b-91ae-364da2661108
Aug. 13, 2025
Action Type Old Value New Value Added Reference https://embracethered.com/blog/posts/2025/github-copilot-remote-code-execution-via-prompt-injection/ Added Reference https://news.ycombinator.com/item?id=44883108 -
New CVE Received by [email protected]
Aug. 12, 2025
Action Type Old Value New Value Added Description Improper neutralization of special elements used in a command ('command injection') in GitHub Copilot and Visual Studio allows an unauthorized attacker to execute code locally. Added CVSS V3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-77 Added Reference https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-53773