AWS bedrock documentation change
Summary
Updated supported APIs for Amazon Bedrock Guardrails by removing 'InvokeAgent' and 'RetrieveAndGenerate' from the integration list.
Security assessment
The change adjusts API integration documentation for a security feature (Automated Reasoning checks) but doesn't indicate any security vulnerability fix. Removal of APIs suggests feature refinement rather than security remediation, with no evidence of patched vulnerabilities or incidents.
Diff
diff --git a/bedrock/latest/userguide/guardrails-automated-reasoning-checks.md b/bedrock/latest/userguide/guardrails-automated-reasoning-checks.md index 7f586bd24..0da306a12 100644 --- a//bedrock/latest/userguide/guardrails-automated-reasoning-checks.md +++ b//bedrock/latest/userguide/guardrails-automated-reasoning-checks.md @@ -78 +78 @@ Using Automated Reasoning checks involves four phases: creating a policy, testin - 4. **Integrate.** At runtime, Automated Reasoning findings are returned through APIs that supports a Amazon Bedrock Guardrails configuration: `Converse`, `InvokeModel`, `InvokeAgent`, and `RetrieveAndGenerate`, as well as the standalone `ApplyGuardrail` API. Inspect the findings to decide whether to serve the response, rewrite it using the feedback, or ask the user for clarification. Automated Reasoning checks operate in _detect mode_ only — they return findings and feedback rather than blocking content. For more information on how to integrate Automated Reasoning checks in your application, see [Integrate Automated Reasoning checks in your application](./integrate-automated-reasoning-checks.html). For more information on the permissions required to enable Automated Reasoning checks, see [Permissions for Automated Reasoning policies with ApplyGuardrail](./guardrail-automated-reasoning-permissions.html). + 4. **Integrate.** At runtime, Automated Reasoning findings are returned through APIs that supports a Amazon Bedrock Guardrails configuration: `Converse`, `InvokeModel`, as well as the standalone `ApplyGuardrail` API. Inspect the findings to decide whether to serve the response, rewrite it using the feedback, or ask the user for clarification. Automated Reasoning checks operate in _detect mode_ only—they return findings and feedback rather than blocking content. For more information on how to integrate Automated Reasoning checks in your application, see [Integrate Automated Reasoning checks in your application](./integrate-automated-reasoning-checks.html). For more information on the permissions required to enable Automated Reasoning checks, see [Permissions for Automated Reasoning policies with ApplyGuardrail](./guardrail-automated-reasoning-permissions.html).