BerriAI/litellm · error · HTTPException

Violated jailbreak threshold

Error message

Violated jailbreak threshold

What it means

Error "Violated jailbreak threshold" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/guardrails/guardrail_hooks/lakera_ai.py:88

        self.api_base = api_base or get_secret("LAKERA_API_BASE") or "https://api.lakera.ai"
        super().__init__(**kwargs)

    #### CALL HOOKS - proxy only ####
    def _check_response_flagged(self, response: dict) -> None:
        _results: Final = response.get("results", [])
        if len(_results) <= 0:
            return

        flagged: Final = _results[0].get("flagged", False)
        category_scores: Final[dict | None] = _results[0].get("category_scores", None)

        if self.category_thresholds is not None:
            if category_scores is not None:
                typed_cat_scores: Final = LakeraCategoryThresholds(**category_scores)
                if "jailbreak" in typed_cat_scores and "jailbreak" in self.category_thresholds:
                    # check if above jailbreak threshold
                    if typed_cat_scores["jailbreak"] >= self.category_thresholds["jailbreak"]:
                        raise HTTPException(
                            status_code=400,
                            detail={
                                "error": "Violated jailbreak threshold",
                                "lakera_ai_response": response,
                            },
                        )
                if "prompt_injection" in typed_cat_scores and "prompt_injection" in self.category_thresholds:
                    if typed_cat_scores["prompt_injection"] >= self.category_thresholds["prompt_injection"]:
                        raise HTTPException(
                            status_code=400,
                            detail={
                                "error": "Violated prompt_injection threshold",
                                "lakera_ai_response": response,
                            },
                        )
        elif flagged is True:
            raise HTTPException(
                status_code=400,

View on GitHub (pinned to 77b7c6c40c)

Solutions

  1. Raise the jailbreak threshold in the lakera_ai guardrail config if legitimate prompts are being flagged.
  2. Rephrase the request to remove jailbreak-like phrasing.

When it happens

Trigger: Thrown at litellm/proxy/guardrails/guardrail_hooks/lakera_ai.py:88 when the library encounters an invalid state.

Common situations: See trigger scenarios.


AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/c5244787c7201d41. Report an issue: GitHub.