Skip to content

Conversation

@prpeh
Copy link
Contributor

@prpeh prpeh commented Mar 25, 2025

  • Add malicious transaction detection using AI models (OpenAI/Gemini)
  • Implement model-switching capability between providers
  • Create UI for displaying and filtering suspicious transactions
  • Add robust error handling to gracefully handle API failures
  • Optimize detection of spam tokens and suspicious addresses

reason: parsedJson.reason || "Analysis completed based on transaction properties."
};
} catch (parseError) {
console.log("First parse attempt failed, trying to extract JSON from text");
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I found that we always encounter the json parsing error, it seems that the ai model return the data in markdown format. If so then we need to handle it properly other than catching it as error.

@prpeh prpeh force-pushed the feature/ai-transaction-security-analysis branch from bf7aa9f to 9b1b49a Compare March 25, 2025 10:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants