Security●●●Banger
OnGarde – Runtime content security proxy for self-hosted AI agents
Transparent proxy blocks agent leaks to LLM APIs without touching agent code.
Solve My ProblemSlick
antimaterial
214mo ago
Back to browse
GitHub Repository
Roles, segregation of duties, and tamper-evident audit for the AI agents you already run. Open-source, self-hosted.
1 starsTypeScript
Scan your AI agents for dangerous capabilities
by smashini·Jul 6, 2026·22 points·12 comments
Similar Projects
Security●●●Banger
I scanned 16 AI agent repos – 76% of tool calls had no guards
Scans for unguarded Stripe refunds and DB deletes before your agent loops.
Solve My ProblemBig Brain
jguarnelli
112mo ago
Security●●●Banger
We scanned 500 ClawHub skills for security risks – 10% were dangerous
19-pattern MCP tool security scanner filling a real gap in agent ecosystem governance.
Solve My ProblemBig Brain
yusufjacobs
314mo ago
Developer Tools●●●Banger
AI agent framework where dangerous actions are structurally unreachable
Session types make dangerous actions code-unreachable, not just policy-blocked.
WizardryBig BrainZero to One
o8vm
304mo ago
AI/ML●●●Banger
Amber, a capability-based runtime/compiler for agent benchmarks
Fuchsia-inspired capability model for agent benchmarks solves reproducibility existing tools ignore.
WizardryBig BrainZero to One
_nhynes
102mo ago
Security●●Solid
Clawsec - Open-source plugin for OpenClaw that blocks dangerous actions
Every tool call is caught by middleware, scored against built-in rulesets like destructive-commands, secrets/* and exfiltration/* in under 5ms, then enforced as block/confirm/allow via a clawsec.yaml — neat, pragmatic attack surface reduction. The demo and auto-generated config make onboarding trivial, but it currently reads as an OpenClaw-first solution; broader agent-framework integrations or stronger isolation guarantees would make this a must-install.
Solve My ProblemNiche GemSlick
subho007
114mo ago