CVE-2026-18733: Prompt injection bypasses shell tool consent gate in Strands Agents Tools
AWS · strands-agents-tools
Fixed in 0.8.0 · Affected: AWS strands-agents-tools before 0.8.0 · Exploitation: unlikely (under 1%)
Not in CyberSIXT coverage yet: no article names this CVE. This page shows the public record.
Higher than 56% of scored CVEs
DescriptionCVE.org
A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the non_interactive parameter to true, bypassing the human consent gate. To remediate this issue, users should upgrade to version 0.8.0.
Affected products1
From the CVE record. A product or version that is not listed is unknown, not unaffected.
- AWS · strands-agents-toolsbefore 0.8.0
On the Atlas
Every published CVE is on the CyberSIXT Atlas, grouped by weakness, vendor and month.
- Exploitation
- Unlikely (under 1%). EPSS under 1%, or no score yet.
- CISA KEV
- Not listed
- Public check
- No public nuclei template
- Vendor
- AWS
- Published
- August 2026
- Bounty reports
- 1 disclosed on HackerOne
Disclosed bug bounty reports about CVE-2026-18733
The reports on HackerOne that name this CVE, with HackerOne's own outcome. Titles and metadata only.
- Unescaped consent-prompt renderer (HTML()) enables concealed-approval OS command injection in strands-agents/tools use_computer — RCEAWS VDP · 2026 · medium severityValid
CoverageNo articles yet
No CyberSIXT article names CVE-2026-18733 yet, so there is no coverage timeline, action brief or change log for it. Everything on this page comes from the public CVE record, CISA KEV, EPSS and the nuclei template index. Search the archive or see the CVEs in the news.