v1

latestOpenAPI 3.0.02026-07-13211133.5 KB

Public Scan

Vulnerability Review

Sends vulnerability details and source code to the AI service, which analyzes the data and returns a classification with a confidence score.

post/api/v2/ai/review

Query parameters

orgstring required

Organization ID

Request body

codestring

A code snippet representing the vulnerable logic or affected lines.

cwe_idstring

CWE identifier, if applicable.

cwe_namestring

Optional name or title of the CWE.

linestring

Line number(s) where the issue appears.

filestring

Name or path of the file containing the snippet.

Example request

{
  "code": "try {\n  const user = db.getUserById(req.query.id);\n  res.send(user);\n} catch (err) {\n  res.status(500).send(\"Error\");\n}\n",
  "cwe_id": "CWE-79",
  "cwe_name": "Cross-Site Scripting",
  "line": "105",
  "file": "userController.js"
}

Response

Successful classification result from the AI model.

class'TRUE_POSITIVE' | 'FALSE_POSITIVE' | 'UNVERIFIED'

The AI-determined classification of the vulnerability.

confidencenumber float

Confidence percentage (0–100) of the classification.

Example response

{
  "class": "TRUE_POSITIVE",
  "confidence": 95.12
}