doronp/agentshield-benchmark
Open benchmark for AI agent security tools — prompt injection, data exfiltration, tool abuse, provenance
Platform-specific configuration:
{
"mcpServers": {
"agentshield-benchmark": {
"command": "npx",
"args": [
"-y",
"agentshield-benchmark"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...