CVE-2026-78379

Summary

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.

Affected Software

VendorProductVersion RangeStatus
Amazonstrands-agents-tools0 < 0.8.5affected

Weaknesses

  • CWE-1427: CWE-1427: Improper Neutralization of Input Used for LLM Prompting

ADP Enrichment

CISA ADP Vulnrichment

  • SSVC:
  • Exploitation: none
    • Automatable: no
    • Technical Impact: total

References