Security & threat coverage

Bridgekeeper reduces and contains the attack classes detection alone misses. Coverage is maintained continuously — see the freshness changelog.

Protection current as of 2026-05-29 18:00 UTC
  • 2026-05-29Indirect injection via retrieved markdown tables
  • 2026-05-22Tool-call argument smuggling (nested JSON)
  • 2026-05-14System-prompt exfiltration via translation request
OWASP LLM riskBridgekeeper control
LLM01 Prompt InjectionUntrusted-content isolation + provenance tracking contain injected instructions.
LLM02 Insecure Output HandlingOutbound/exfiltration controls gate what the model can emit and where.
LLM06 Sensitive Information DisclosureProvenance marks system/secret content non-disclosable.
LLM07 Insecure Plugin DesignTool/function-call authorization gates privileged calls.
LLM08 Excessive AgencyAuthorization + outbound control bound what actions the model can take.