Scam2Prompt is a framework that converts scam-site intents into developer-style prompts and measures how often production LLMs generate malicious code, finding rates from 4.24% to 47.3% across eleven models and showing that current guardrails do not block the behavior.
4.5 million (suspected) fake stars in github: A growing spiral of popularity contests, scams, and malware,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
Introduces a theory-based framework with 10 variables to build a repository-level psychological safety index from 60k+ PRs and finds positive links to short- and long-term contributor retention, though prior activity is the stronger predictor.
citing papers explorer
-
Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
Scam2Prompt is a framework that converts scam-site intents into developer-style prompts and measures how often production LLMs generate malicious code, finding rates from 4.24% to 47.3% across eleven models and showing that current guardrails do not block the behavior.
-
Psychological Safety Framework in Pull-based Open Source Projects
Introduces a theory-based framework with 10 variables to build a repository-level psychological safety index from 60k+ PRs and finds positive links to short- and long-term contributor retention, though prior activity is the stronger predictor.