Back to evaluations
Public evaluation
scam_report_triage
Evaluates Google ADK agent accuracy in identifying scam domains and outputting standardized incident response directives.
Evaluation type
task based
Challenge
Anti-Scam Root Cause Triage Agent with Google ADK and Gemini
Difficulty
Intermediate
Rigor
Unspecified
Evaluation overview
How the linked challenge is judged: tasks, benchmarks, and criteria count.
Tasks
1
Benchmarks
0
Criteria
0
Task templates
Inputs and expected outputs.
Task 1
scam_report_triage
Tests extraction of phishing URLs, target brand impersonation, and threat escalation level.
Input format
JSON containing SMS text body and base64 encoded screenshot metadata
Output format
JSON containing extracted_urls, impersonated_entity, threat_level, and takedown_recommended