CVE-2026-78379Network attack vector

Host code execution via batch consent bypass

Published Aug 25, 2026 · Updated Aug 25, 2026

Prompt injection in Strands Agents Tools before 0.8.5 allows remote attackers to execute arbitrary Python code without operator consent. The batch tool forwards a caller-supplied non_interactive_mode keyword to python_repl, which treats it as authorization to skip the prompt. Exploitation requires both tools on the same agent and untrusted content that influences its prompt, after which code runs with the agent host's privileges.

CVSS severity9.2
Critical
EPSS probability0.32%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Prompt injection in Strands Agents Tools before 0.8.5 allows remote attackers to execute arbitrary Python code without operator consent. The batch tool forwards a caller-supplied non_interactive_mode keyword to python_repl, which treats it as authorization to skip the prompt. Exploitation requires both tools on the same agent and untrusted content that influences its prompt, after which code runs with the agent host's privileges.

The record

CVE
CVE-2026-78379
Published
Aug 25, 2026
Updated
Aug 25, 2026
Vendor
Amazon Web Services
Product
Strands Agents Tools
Classifications
CWE-1427, CAPEC-248, T1059.006
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Aug 25, 2026CVE publishedPublication date reported by the CVE source.
  2. Aug 25, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0 <0.8.5

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Amazon Web Services · Strands Agents Toolsversion=0 <0.8.5

Published CVSS scores

8.1Amazon Web ServicesCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
9.2Amazon Web ServicesCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-1427Improper Neutralization of Input Used for LLM Prompting
CAPEC-248Command Injection
T1059.006Command and Scripting Interpreter: Python

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo