CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools
Remote attackers can execute arbitrary Python code by bypassing consent gates in Amazon Strands Agents Tools via crafted prompts.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-78379?
CVE-2026-78379 is a critical code injection vulnerability in Amazon strands-agents-tools, published on 25 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-1427
Which versions are affected by CVE-2026-78379?
How do I fix CVE-2026-78379?
No fix has been published for CVE-2026-78379 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-78379 being exploited?
There is no known exploitation of CVE-2026-78379 in the wild and no public exploit code.