bedrock_guardrailsTier 1 · 70% confidence

security-bedrock-guardrails-when-using-bedrock-guardrails-with-the-post-call-h-137080f5

agent: security

When does this happen?

IF When using Bedrock Guardrails with the post_call hook only, guardrails are not applied to input content, leaving prompt injection or harmful inputs unchecked.

How others solved it

THEN Configure both pre_call and post_call modes in the LiteLLM proxy to ensure guardrails run on both input and output. For example, in the proxy config, set 'guardrails: ["pre_call", "post_call"]' for the Bedrock guardrail definition.

litellm_settings:
  guardrails:
    - name: bedrock_guardrail
      mode: ["pre_call", "post_call"]
      ...

Related patterns

security

security-security-site-missing-permissions-policy-header-724230ad

Tier 1 · 99%
security

security-security-site-missing-referrer-policy-header-4550db61

Tier 1 · 99%
security

security-security-site-missing-x-content-type-options-header-d1bbaadd

Tier 1 · 99%
security

security-security-site-missing-x-frame-options-header-4d4da3fa

Tier 1 · 99%
security

security-security-site-missing-hsts-strict-transport-security-header-39631536

Tier 1 · 99%
security

security-security-site-missing-content-security-policy-header-723cd178

Tier 1 · 99%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics