CRITICAL 9.2 NVD
CVE-2026-78379
Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute
Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.
References
- https://aws.amazon.com/security/security-bulletins/2026-089-aws/
- https://pypi.org/project/strands-agents-tools/0.8.5/
This critical severity vulnerability with a CVSS score of 9.2 was published on 2026-08-25 via NVD.
Risk Timeline
CVE Disclosed2026-08-25 · -1 days ago
Remediation Resources
Official Advisory
aws.amazon.com/security/security-bulletins/2026-089-aws/Analysis & PoC
pypi.org/project/strands-agents-tools/0.8.5/
vulnfeed aggregates 11950 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.