CVE-2026-78379 - Consent bypass in Strands Agents Tools python_repl tool

unknownCVE-2026-78379

Bulletin ID: 2026-089-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/25/2026 12:00 PM PDT Description: Strands Agents is an open-source Python SDK for building and running AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the python_repl tool, which executes Python code on the agent's host, and the batch tool, which invokes several other tools in a single call. Before executing code, python_repl prompts the operator for approval. We identified CVE-2026-78379, a consent bypass in the python_repl tool. 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. Impacted versions: < 0.8.5 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

CSIRTS triage

vendor: Amazon product: Strands Agents Tools Authentication bypass Code injectionaffected: Before 0.8.5

What: A consent bypass vulnerability in the python_repl tool allows remote attackers to execute arbitrary Python code by bypassing the human approval gate through crafted LLM prompts.
Who is affected: AI agents using Strands Agents Tools python_repl before version 0.8.5 that process untrusted LLM-generated input.
Urgency: High; allows arbitrary code execution on agent hosts via prompt injection without user consent.
Action: Upgrade strands-agents-tools to version 0.8.5 or later.

AI-assisted analysis generated from the source advisory — verify against the original.

⚡ Watch Strands Agents Tools

Get an email when a new Strands Agents Tools advisory drops — max one per day, one-click unsubscribe.

Details

Source: AWS Security Bulletins (INTL · vendor-psirt · site)
Severity: unknown
Published: 2026-09-09
Exploitation: Not in CISA KEV at last sync

Original advisory: https://aws.amazon.com/security/security-bulletins/rss/2026-089-aws/

Exploitation outlook

EPSS (FIRST.org) estimates each CVE’s probability of exploitation in the next 30 days — here is the CSIRTS.com read on those numbers.

Low exploitation riskCVE-2026-783790.32% 30-day exploitation probability — currently an unlikely target, but scores change as exploit code circulates. Riskier than 25% of all EPSS-scored CVEs.

Referenced CVEs

CVE	CSIRTS overview	External
CVE-2026-78379	coverage & exploitation status	NVD · CVE.org

Same CVEs, other sources

How other CERTs, PSIRTs and databases cover the vulnerabilities in this advisory.

highCVE-2026-78379: Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Stra…nvd

Recent advisories for - Consent bypass

A cluster of recent advisories against the same product widens the attack surface — attackers routinely chain freshly published CVEs on one product, so review these together.

unknownCVE-2026-86793: SGLang allows unauthenticated pickle deserialization through /update_weights_from_tensor when …nvd · 2026-09-11
highCVE-2026-80469: An attacker may achieve arbitrary code execution on a target system by uploading a malicious d…nvd · 2026-09-11
mediumCVE-2026-89175: Smart Video Intercom System developed by Kingdom Communication Associated has a Client-Side Au…nvd · 2026-09-11
unknownCVE-2026-89169: live-boot ff8867c allows attackers to bypass the dm-verity-enforce-roothash-signature protecti…nvd · 2026-09-11
mediumCVE-2026-12215: The OTP Login & Register Woocommerce plugin for WordPress is vulnerable to Authentication Bypa…nvd · 2026-09-11
unknownCVE-2026-88260: Authentication bypass using an alternate path or channel and Improper validation of syntactic …nvd · 2026-09-11