Wolf Defender, a open-weight prompt-injection detection model
Outperforms existing open-source injection detectors on ProtectAI and Qualifire benchmarks.

Dynamic LLM sandbox analysis detects injections that static pattern matching tools miss.
LLM application developers, Security engineers
Lakera Guard · PromptArmor · Rebuff
Outperforms existing open-source injection detectors on ProtectAI and Qualifire benchmarks.
Semgrep for AI agents—138 rules, offline, catches obfuscated attacks other scanners miss.
Catches infinite loops and injection risks without running the agent, but Snyk+Semgrep+manual review already covers this.
Maps cross-agent injection attacks to real Copilot CVEs with live measurements.
Another guardrail API competing with Lakera, but claims sub-30ms latency.
Yet another LLM ops layer when LangSmith, Helicone, and Braintrust already exist.