BerriAI/litellm · error · HTTPException

File blocked by Prompt Security. Violations: {', '.join(viol

Error message

File blocked by Prompt Security. Violations: {', '.join(violations)}

What it means

Error "File blocked by Prompt Security. Violations: {', '.join(violations)}" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py:467

        if not url.startswith("data:"):
            return item

        try:
            header, encoded = url.split(",", 1)
            file_data: Final = base64.b64decode(encoded)
            mime_type: Final = header.split(";")[0].split(":")[1]
            extension: Final = mime_type.split("/")[-1]
            filename: Final = f"image.{extension}"

            sanitization_result: Final = await self.sanitize_file_content(
                file_data, filename, user_api_key_alias=user_api_key_alias
            )
            action: Final = sanitization_result.get("action")

            if action == "block":
                violations: Final = sanitization_result.get("violations", [])
                raise HTTPException(
                    status_code=400,
                    detail=f"File blocked by Prompt Security. Violations: {', '.join(violations)}",
                )

            if action == "modify":
                sanitized_content: Final = sanitization_result.get("content", "")
                if sanitized_content:
                    sanitized_encoded: Final = base64.b64encode(sanitized_content.encode()).decode()
                    sanitized_url: Final = f"{header},{sanitized_encoded}"
                    if isinstance(image_url_data, dict):
                        image_url_data["url"] = sanitized_url
                    else:
                        item["image_url"] = sanitized_url
                    verbose_proxy_logger.info("File content modified by Prompt Security")

            return item
        except HTTPException:
            raise

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Remove the violating content from the file before sending.
2. Review the Prompt Security file scanning policies that produced the violations.

When it happens

Trigger: Thrown at litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py:467 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/ec1de258203a4deb. Report an issue: GitHub.