GHSA-j6g5-3hh3-pgw8: AWS Bedrock AgentCore: Improper neutralization of argument delimiters in the Python SDK install_packages()
- Identifiers
- CVE-2026-16796GHSA-j6g5-3hh3-pgw8
- Published
- Record updated
- Affected
- bedrock-agentcore < 1.18.1
- Fixed in
- 1.18.1
- released July 17, 2026, 7 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.7%
Summary
The AWS Bedrock AgentCore Python SDK (bedrock-agentcore), before 1.18.1, has improper neutralization of argument delimiters in its install_packages() method. Under certain circumstances, a remote authenticated user can craft package name arguments that bypass input validation and execute arbitrary commands within the Code Interpreter sandbox.
Mitigation
Fixed in bedrock-agentcore 1.18.1. Upgrade to the latest version and patch any forked or derivative code. If upgrading is not possible, do not pass untrusted or model-generated input to install_packages(), and validate dynamic package names against strict PyPI naming rules, constraining any extras group to comma-separated identifiers, before calling the SDK.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- bedrock-agentcorePyPILLM dependency since 2025-09-05 · 4 tracked dependents
Related items
- MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
- MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
- HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
- InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
- MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online