Audit text for indirect personal identifiers
Scan drafted text for subtle quasi-identifiers, niche titles, and contextual details that could de-anonymize individuals.
You getFindings Table, privacy Audit Summary and immediate Next Actions
Prompt
Act as a privacy auditor. Inspect the pasted text below for indirect, contextual, or quasi-identifiers that could reveal an individual or organization even without explicit names.
- Flag hyper-specific job titles, niche locations, distinctive project milestones, or rare date combinations.
- Identify combinations of attributes that allow re-identification through cross-referencing.
- Evaluate each risk as High, Medium, or Low based on re-identification likelihood.
- Suggest an abstract, generalized replacement for every flagged detail.
Output format:
1. Findings Table (columns: Quoted Snippet, Identifier Risk, Severity, Recommended Generic Replacement)
2. Privacy Audit Summary (2-3 sentences assessing overall privacy exposure)
3. Immediate Next Actions (numbered list of changes required before external sharing)
Text to audit:Example output
Paste meeting recaps, incident reports, or case studies into ChatGPT, Claude, or Gemini. Ask the model to re-run the check with higher sensitivity if your team handles medical or regulated financial records.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Evaluate task safety and privacy for AI drafting
Assess whether a specific task or text draft is safe to process with an AI model based on privacy, accuracy, and professional stakes.
Build a reversible token map for anonymization
Create a structured token substitution table and sanitized copy of sensitive documents to enable clean round-trip anonymization.
Uncover hidden assumptions in an AI response
Reveals the unstated guesses, missing variables, and implied context inside an AI answer so you can make informed decisions.
Audit drafts for confidently phrased factual hallucinations
Scans generated text for high-risk assertions, unverified statistics, and false certainty. Use it before publishing AI-written reports or summaries.
Scrub sensitive names and secrets from text
Remove personal names, client details, passwords, and API keys from raw logs or text while keeping technical context intact.
Audit AI text for hidden bias and one-sided framing
Detect subtle assumptions, suppressed counterarguments, and one-sided framing in an existing AI-generated answer.
- Spot formatting regressions across model updates
- Synthesize multi-chunk summaries without losing details
- Answer questions while highlighting unknown facts
- Create a reusable library of personal AI prompts
- Ground every conclusion in exact source quotes
- Process pasted text between clear start and end markers