BerriAI/litellm · error · PromptSecurityGuardrailMissingSecrets

Couldn't get Prompt Security api base or key, either set the

Error message

Couldn't get Prompt Security api base or key, either set the `PROMPT_SECURITY_API_BASE` and `PROMPT_SECURITY_API_KEY` in the environment or pass them as parameters to the guardrail in the config file

What it means

Error "Couldn't get Prompt Security api base or key, either set the `PROMPT_SECURITY_API_BASE` and `PROMPT_SECURITY_API_KEY` in the environment or pass them as parameters to the guardrail in the config file" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py:69

        self.user = user or os.environ.get("PROMPT_SECURITY_USER")
        self.system_prompt = system_prompt or os.environ.get("PROMPT_SECURITY_SYSTEM_PROMPT")

        # Configure whether to check tool/function results for indirect prompt injection
        # Default: False (Filter out tool/function messages)
        # True: Transform to "other" role and send to API
        if check_tool_results is None:
            check_tool_results_env: Final = os.environ.get("PROMPT_SECURITY_CHECK_TOOL_RESULTS", "false").lower()
            self.check_tool_results = check_tool_results_env in ("true", "1", "yes")
        else:
            self.check_tool_results = check_tool_results

        if not self.api_key or not self.api_base:
            msg: Final = (
                "Couldn't get Prompt Security api base or key, "
                "either set the `PROMPT_SECURITY_API_BASE` and `PROMPT_SECURITY_API_KEY` in the environment "
                "or pass them as parameters to the guardrail in the config file"
            )
            raise PromptSecurityGuardrailMissingSecrets(msg)

        # Configuration for file sanitization
        self.max_poll_attempts = 30  # Maximum number of polling attempts
        self.poll_interval = 2  # Seconds between polling attempts

        super().__init__(**kwargs)

    def supports_scan_only_tool_results(self) -> bool:
        return self.check_tool_results

    @log_guardrail_information
    async def apply_guardrail(
        self,
        inputs: GenericGuardrailAPIInputs,
        request_data: dict,
        input_type: Literal["request", "response"],
        logging_obj: Optional["LiteLLMLoggingObj"] = None,
    ) -> GenericGuardrailAPIInputs:

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set PROMPT_SECURITY_API_BASE and PROMPT_SECURITY_API_KEY environment variables.
2. Or pass api_base and api_key in the prompt_security guardrail's litellm_params.

When it happens

Trigger: Thrown at litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py:69 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/7e9cc8474001077f. Report an issue: GitHub.