Guardrails
How Telflo keeps AI interactions safe, private, and on topic.
Messages you send to the assistant, and the responses it returns, pass through guardrails. Guardrails block prompt injection and abuse, keep sensitive data out of requests and responses, and keep the assistant focused on OpenTelemetry. Which checks run depends on the mode. When a blocking guardrail is triggered, the assistant returns a safe message and asks you to rephrase.
Input guardrails
Checked on what you send.
| Guardrail | What it catches |
|---|---|
| Prompt injection | Jailbreak attempts, role overrides, and attempts to extract or override the assistant's instructions. Blocks the request. |
| Malicious intent | Requests aimed at data exfiltration, credential exposure, or network attacks. Blocks the request. |
| PII | Personal information in a prompt. Warns without blocking. |
Output guardrails
Checked on what the assistant returns.
| Guardrail | What it catches |
|---|---|
| YAML safety | Dangerous endpoints or hardcoded secrets in generated configuration. |
| PII and secrets | API keys, credentials, or personal data in a response. |
| Relevance | Off-topic answers, keeping the assistant on OpenTelemetry. |
What you see
When a blocking guardrail is triggered, the assistant returns a safe message instead of the blocked content and suggests how to rephrase the request.
Keep secrets out of prompts
Avoid pasting real keys or endpoints into the chat. Reference credentials as environment variables with ${env:NAME} in the configuration, so they stay out of prompts and out of the YAML. For shared non-secret values such as endpoints, reference an organization variable with $orgvar:NAME; the token stays in the YAML and is resolved when each collector checks in.
Last updated on