Screen CVs for hidden prompt injections with Gemini, Google Drive, Sheets, and Telegram
Quick overview Youtube Video: https://youtu.be/WMB6WwJayc
Quick overview
Youtube Video: https://youtu.be/WMB_6WwJayc
This workflow collects PDF CVs via an n8n form, screens them twice with Gemini (text extraction and vision on a rendered image), and compares the results to detect hidden-text, prompt-injection attempts, then quarantines suspicious files in GDrive and logs outcomes to Sheets with Telegram.
How it works
- Receives a job application submission via an n8n form with the candidate’s name, selected role, and a PDF CV upload.
- Validates that the uploaded file is a PDF and returns a rejection form response if the format is incorrect.
- Extracts raw text from the PDF and sends it to Google Gemini to produce a structured verdict (qualified flag, score, years of experience, and one-sentence reason).
- Converts the PDF to a JPG via ConvertAPI, converts the returned base64 to an image file, and sends the image to Google Gemini vision to generate the same structured verdict (and reports via Telegram if this vision path fails).
- Compares the text and vision verdicts to compute score and experience gaps and flags the CV as suspicious if the verdicts disagree or diverge beyond the configured thresholds.
- If flagged, uploads the original CV to a Google Drive quarantine folder and sends a detailed Telegram alert; otherwise, sends a “clean result” Telegram message using the vision-based reason.
- Appends a row to a Google Sheets “Applications” tab with the submission metadata, both scores, divergence metrics, the suspicion flag, and the trusted reason.
Setup
- Configure the n8n form trigger and publish the form so candidates can submit their name, role, and a PDF file in the binary field named "CV".
- Add Google Gemini (PaLM) credentials and ensure the selected Gemini model supports both text and multimodal inputs.
- Set up ConvertAPI and replace the placeholder Secret in the PDF-to-JPG HTTP request URL.
- Add Google Drive OAuth2 credentials and set the target quarantine folder ID.
- Add Google Sheets OAuth2 credentials and update the spreadsheet ID and ensure the “Applications” tab has the expected headers.
- Add Telegram bot credentials and replace the placeholder chat ID(s) for the flagged, clean, and vision-failure notifications.
production deployment
Need this workflow deployed or tailored for your business?
I customize n8n pipelines, build proprietary API nodes, and connect production databases with sub-100ms reliability.
creator
iamvaar
Top 50 Verified Creator
AI Automation Engineer building production-grade n8n systems, custom nodes, and LLM pipelines.
n8n.io/creators/iamvaarspecs
related automations
More workflows from iamvaar
Screen and triage job applications with Gemini, Google Sheets, Slack and Gmail
Quick overview Youtube Video: https://www.linkedin.com/posts/iamvaarn8n-aiautomation-recruitingtech-activity-7503103988427542528-9X1G
Route weather-based delivery holds with Open-Meteo, Gemini, Postgres, and ServiceNow
Quick overview Demo Video: https://youtu.be/ccEy0J-LKY
Track daily LLM brand visibility with Gemini, Groq, OpenRouter, Sheets and Slack
Quick overview Youtube Video: https://youtu.be/BOodBD6HWSU?si=yEenUFBdYOq1RVj This workflow runs daily at 7AM to generate buyer-style prompts with Google Gemini, query Groq, Ope...
Want this workflow running in your stack?
Book a free 30-minute session. I'll inspect your current infrastructure, review required API credentials, and map out the deployment.