malicious-prompts
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Malicious Prompts English (test)
100ASR@5
72
16 malicious prompts
0ASR
40
792 malicious prompts MCP vulnerabilities 1.0 (test)
0.04ASR (Trial)
8
Malicious Prompts
372.38FID-Censored
6
ahsanayub/malicious-prompts
98.72Accuracy
4