AgentShield-Bench
Collection
Agent security benchmark for tool-calling and MCP environments — dataset, classifiers, secure agent pipeline, and interactive evaluation. • 7 items • Updated
AgentShield Content Trust Classifier
Labels retrieval and untrusted content as trusted or untrusted for agent consumption.
Usage
from setfit import SetFitModel
model = SetFitModel.from_pretrained("alirezaaminzadeh/agentshield-content-trust-classifier")
print(model.predict(["Standard support ticket with no suspicious content"])) # [0]
License
Apache 2.0
Model tree for alirezaaminzadeh/agentshield-content-trust-classifier
Base model
nreimers/MiniLM-L6-H384-uncased Quantized
sentence-transformers/all-MiniLM-L6-v2