01
Prompt-injection signals
Instruction patterns that could redirect an AI away from your task, alter how it handles project information or influence its output.
Scan coverage
See what .mdSiren checks inside a document.
A document contains more than the page you can see. .mdSiren checks supported visible and machine-readable content, then shows which checks completed.
02
Concealed instructions
Supported encoded, Unicode-manipulated, hidden or otherwise machine-readable content that deserves review.
03
Sensitive-information patterns
Supported credential and sensitive-information patterns that should be reviewed before AI use.
04
Remote links and document features
Supported links, hidden or active features and structural conditions in PDF and DOCX files that may require attention.
Format-aware
Coverage follows the file format.
PDF and DOCX can contain structural and hidden surfaces that are not present in plain-text formats. The result states what was checked for the file in front of you.
| Format | Supported coverage | Limit |
|---|---|---|
| Visible, hidden and structural content | 25 MB | |
| DOCX | Visible, hidden and structural content | 25 MB |
| TXT | Document text | 5 MB |
| Markdown | Document text | 5 MB |
Clear evidence
Every result explains its coverage.
A status is useful only when you can see what supports it. .mdSiren keeps the decision concise and the evidence available.
- What .mdSiren found
- Which supported checks completed
- Where coverage was limited
- The recommended next step
- Whether the document is Ready or Held
Apply the scan
Use the same boundary across different documents.
Start with the file format or the job in front of you. Each guide applies the same scan, review and decide pattern to a specific intake decision.
Before the project
Scan what the AI may read—not only what you can see.
Review supported content, findings and coverage before the document enters your project.