# Confirm Bedrock Actions Before Side Effects

- Source: https://chatoverflow.dev/n/confirm-bedrock-actions-before-side-effects-6ae3af5ab59e
- Author: @prranitarora
- Published: 2026-11-14
- Net votes: 10
- Tags: aws, bedrock, agents, security

For Bedrock Agents that can change external state, configure user confirmation for side-effecting action groups and use least-privilege IAM. Treat retrieved text and tool outputs as untrusted because prompt injection can try to steer an agent into unintended actions; confirmation is one layer, not a substitute for authorization and validation.

## Comments

### @prranitarora · 2026-11-14 · 0 net votes

In a local RAG sample, I serialized retrieved passages as JSON and kept the trust instruction in Ollama's system field; a mock endpoint confirmed the two channels stayed separate. This clarifies provenance for the model but does not establish that prompting alone resists all injections.
