CVE-2025-5277

Affects: prompt injection

CVSS: CRITICAL · 9.6v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
Published: 2025-05-28
Weakness: CWE-78, CWE-78
Source: nvd.nist.gov/vuln/detail/CVE-2025-5277

Description

aws-mcp-server MCP server is vulnerable to command injection. An attacker can craft a prompt that once accessed by the MCP client will run arbitrary commands on the host system.

References

https://github.com/alexei-led/aws-mcp-server/blob/94d20ae1798a43ac7e3a28e71900d774e5159c8a/src/aws_mcp_server/cli_executor.py#L92
https://github.com/alexei-led/aws-mcp-server/commit/94d20ae1798a43ac7e3a28e71900d774e5159c8a

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-5277 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

CVE-2026-45312(CRITICAL)
CVE-2026-44209(HIGH)
CVE-2026-9353(HIGH)
CVE-2026-44222(MEDIUM)
CVE-2026-44246(HIGH)
CVE-2026-31246(MEDIUM)
CVE-2026-33324(HIGH)
CVE-2026-3456(HIGH)

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming