CVE-2026-78379
Prompt injection in Amazon Strands python_repl allows remote arbitrary Python execution.
Is CVE-2026-78379 being exploited?
Not confirmed. CVE-2026-78379 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.32% probability of exploitation in the next 30 days.
How severe is CVE-2026-78379?
CVE-2026-78379 is rated Critical with a CVSS score of 9.2. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2026-78379?
Yes. A fix has been recorded for CVE-2026-78379. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-78379 affect?
CVE-2026-78379 affects Amazon Strands Agents Tools <0.8.5, python_repl tool, batch tool. Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-78379?
Upgrade to Amazon Strands Agents Tools >=0.8.5; isolate agents and restrict network access.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Remote attackers can bypass the human-consent gate and execute arbitrary Python on the agent host via crafted prompts forwarding non_interactive_mode.
Immediate action required
- affected< 0.8.5
As published in the CVE Program record. A version outside these ranges is not a statement that it is unaffected — vendors sometimes understate a range, and distribution-backported builds carry upstream numbers that do not reflect what was patched into them.