CVE-2026-18733 Prompt injection bypasses shell tool consent gate in Strands Agents Tools
HighCVSS 7.5
EPSS 0.78%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- No known exploitation · automatable: no · technical impact: total
Description
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.
Upgrade path
1 package: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| AWS strands-agents-tools | < 0.8.0 | 0.8.0 | Fixed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| AWS strands-agents-tools | < 0.8.0 | 0.8.0 |
References
- pypi.org patch release-notes
- aws.amazon.com vendor-advisory
- github.com release-notes