Control

Prompt injection protection

BaseLLM looks for instructions aimed at steering the model in the messages it sends on: ignoring earlier instructions, leaking the system prompt, switching roles and the like. Protection is turned on per project; your applications need no changes.

Three modes

ModeWhat happens to the request
OffNo scan. This is the default for a new project.
ReportThe request goes through unchanged; an event is recorded.
BlockIf the verdict is an attack, the request is rejected with 403 injection_blocked and never reaches the model.

How the scan works

User and tool messages are scanned; the system prompt is not. Text is cleaned before the scan: invisible characters are removed, Cyrillic letters standing in for Latin ones are fixed, and base64-hidden text is decoded. Then three stages run:

  • Rule filter stage 1: Seven pattern groups: override, leak, persona switch, exfiltration, stealth, obfuscation and English patterns.
  • Classifier models stage 2: Two models running on the server: one for Turkish and one multilingual. Without the models installed, the rule filter decides alone.
  • Local LLM stage 3: Gives a third opinion on a suspicion only one signal raised. Runs when your own verification model is configured.

A block needs two signals to agree: a rule and a model, or both models. A single signal is only recorded. There are two exceptions: when the models cannot answer, a rule decides alone; on English text, the multilingual model's flag is enough.

Local LLM settingWhat happens
OffSingle-signal suspicions are only recorded.
Background (default)The request does not wait; the LLM labels the event afterwards.
Wait (strict)In Block mode, suspicions that could become a block wait for the LLM; an "attack" verdict rejects the request.

Chat, Decisions and embeddings requests are scanned, as are document chunks and search queries sent to the Knowledge Catalogue.

Records, reports and SIEM

  • Message text is not stored; only the matched phrase (up to 120 characters), the rule group, model scores and counters are kept.
  • Reported and blocked events are also written to the audit log.
  • Events are kept for 90 days by default. Change this with INJECTION_EVENT_RETENTION_DAYS in Settings; 0 keeps them forever.
  • Events are exported to SIEM on the injection channel and have their own section in the Project Report.
  • The try box on the screen runs a sample text through the rule filter; the test is not sent anywhere and not recorded.
CaseHTTPError codeMessage
Attack in Block mode403injection_blockedRequest blocked: the message contains instructions aimed at the model (prompt injection).