CVE-2026-78379
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.
Scoring
- Severity
- CRITICAL
- CVSS base score
- 9.2
- CVSS vector
- CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- EPSS probability
- 0.32%
- CWE
- CWE-1427
- Published
- 2026-08-25
- Last modified
- 2026-08-25
Affected products
- Amazon strands-agents-tools
Weakness type
Related vulnerabilities
- CVE-2026-70331 — Microsoft Edge for iOS Spoofing Vulnerability
- CVE-2026-75130 — Context7 2.1.2 Prompt Injection via Custom AI Instructions
- CVE-2026-21832 — HCL AION is affected by multiple security vulnerabilities.
- CVE-2026-18733 — Prompt injection bypasses shell tool consent gate in Strands Agents Tools
- CVE-2026-15077 — Improper Neutralization of Input Used for LLM Prompting in GitLab
- CVE-2026-46580 — In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in...
- CVE-2026-44688 — In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory...
- CVE-2026-44717 — MCP Calculate Server: Prompt Injection to RCE