Choose
Select a supported document before adding it to your AI project. The original remains unchanged.
Document security for AI projects
Outside documents can contain hidden instructions that an AI can read and follow. .mdSiren scans them first, flags what needs review, and gives you a clear next step before they influence your work.
Example scan result
Market conditions remained mixed across the selected categories. The visible summary continues on the following page.
Finding 01
A concealed passage may try to redirect an AI away from your task. Keep this document out of the project while you review it.
Checks completed
The risk
AI projects build on the material you give them. If a document carries a prompt-injection instruction, it can steer the first response and continue shaping the analysis, drafts and decisions that follow.
.mdSiren gives you a chance to review that influence before the document becomes part of the project.
Learn about prompt injection in documentsHow it works
One deliberate step before an outside file starts influencing the work.
Select a supported document before adding it to your AI project. The original remains unchanged.
.mdSiren checks supported visible and hidden content for prompt-injection signals and other risks.
Review the status, findings, coverage and recommended next step before using the document.
What it scans
.mdSiren checks supported visible and machine-readable content, then shows what completed and where coverage was limited.
Ready or Held
The status leads. The findings, completed checks and coverage explain why.
No findings requiring review
Every required supported check completed without a supported reason to hold the document.
Review required
Something needs review, or the required supported checks did not complete.
Use cases
Use the same intake boundary wherever external files meet AI-assisted work.
Scan reports, papers and source packs before AI-assisted analysis or synthesis.
Explore research document scanningScan briefs, contracts and deliverables before they influence client projects.
Explore client document scanningScan CVs, portfolios and candidate files before AI-assisted summarisation or human review.
Explore candidate document scanningLocal processing
.mdSiren scans supported document content in your browser. The original remains on your device and stays unchanged.
If you choose to save scan history, it remains locally in this browser on this device.
How local processing worksFrom the blog
Practical guidance on prompt injection, document security and safer AI workflows.
Learn how instructions inside external documents can influence AI, why the impact varies, and where a document scan fits.
Read articleFollow the path from a document’s hidden content to an AI model—and see where a scan can interrupt that path.
Read articleA PDF can contain more than its rendered pages. Learn which machine-readable surfaces matter before using one with AI.
Read articleCommon questions
Supported prompt-injection signals, concealed instructions, sensitive-information patterns, remote links and active document features.
The supported scan runs in your browser, on your device. The original stays unchanged.
Ready means every required supported check completed without a supported reason to hold the document. Held means something needs review or a required check did not complete.
Before the project
See what the document contains, what .mdSiren checked and what needs review.