Answer in brief
CVE-2026-18733 records a High severity (CVSS 8.8) vulnerability in Prompt injection bypasses shell tool consent gate in Strands Agents Tools. The current sources do not mark it as known exploited. The current feed maps AWS/strands-agents-tools (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps AWS/strands-agents-tools (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| AWS/strands-agents-toolsgeneric | >=0 <0.8.0 | 0.8.0 |
Published upstream
Aug 3, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 4, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 3, 2026
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.
Quoted source text, attributed separately from HOL analysis.
Answer in brief
CVE-2026-18733 records a High severity (CVSS 8.8) vulnerability in Prompt injection bypasses shell tool consent gate in Strands Agents Tools. The current sources do not mark it as known exploited. The current feed maps AWS/strands-agents-tools (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps AWS/strands-agents-tools (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| AWS/strands-agents-toolsgeneric | >=0 <0.8.0 | 0.8.0 |
Published upstream
Aug 3, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 4, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 3, 2026
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.
Quoted source text, attributed separately from HOL analysis.