21
total weekly downloads
3 packages
@opensecureai/agent-guard
Dependency-free static analyzer that audits LLM agent tool/function definitions (OpenAI, Anthropic, MCP) for excessive agency, code-execution & SSRF sinks, secret access, and data-exfiltration surface — mapped to the OWASP 2025 LLM Top-10. Runs in CI.
@opensecureai/firewall
Dependency-light LLM guardrail that decides whether text should be allowed, flagged, or blocked before it reaches a model — composing prompt-injection detection with PII/secret redaction under a configurable policy.
@opensecureai/scanner
Dependency-free heuristic scanner that detects prompt-injection, jailbreak, and data-exfiltration patterns in untrusted text before it reaches an LLM.