# Trident

## Docs

- [Review and Manage Security Findings in Trident](https://docs.usetrident.dev/agents/findings.md): Trident's Findings inbox aggregates security issues from red-team runs, the runtime firewall, static analysis, monitors, and agent self-reports.
- [Runtime Firewall: Protect Agents from Prompt Injection](https://docs.usetrident.dev/agents/firewall.md): Trident's runtime firewall scans every prompt and output for prompt injection, jailbreaks, and data exfiltration attempts in real time.
- [AI Agent Security: Trace, Test, and Protect in Production](https://docs.usetrident.dev/agents/overview.md): An overview of Trident's agent security capabilities: distributed tracing, automated red-teaming, runtime firewall, and findings management.
- [Automated Red-Teaming for AI Agents](https://docs.usetrident.dev/agents/red-teaming.md): Run automated adversarial attack campaigns against your AI agents using Trident's 200+ built-in attack vectors covering the OWASP Agentic Top-10.
- [Trace AI Agent Activity with Trident SDK](https://docs.usetrident.dev/agents/tracing.md): Automatically capture every prompt, tool call, and LLM response your agent makes using the Trident SDK — with zero-config PII redaction.
- [Agents API: List and Query Your AI Agent Inventory](https://docs.usetrident.dev/api/agents.md): GET /api/public/trident/agents — list all agents registered in your Trident project, with their IDs, cert scores, and open finding counts.
- [API Authentication: Keys, Headers, and Rate Limits](https://docs.usetrident.dev/api/authentication.md): Trident's REST API uses HTTP Basic authentication with your project Public Key and Secret Key. Learn how to construct and pass your credentials.
- [Findings API: Query Security Issues Programmatically](https://docs.usetrident.dev/api/findings.md): GET /api/public/trident/findings — retrieve security findings from red-team, firewall, SAST, and cloud scanners with filtering and pagination.
- [Firewall API: Scan Prompts and View Project Ban Rules](https://docs.usetrident.dev/api/firewall.md): POST /api/public/trident/scan scans prompts for injection attacks. GET /api/public/trident/firewall/rules fetches active ban rules for your project.
- [LLM Gateway API: OpenAI and Anthropic Proxy Endpoints](https://docs.usetrident.dev/api/gateway.md): Trident's gateway endpoints are drop-in replacements for OpenAI and Anthropic, routing all LLM calls through the runtime firewall with full tracing.
- [Red-Team API: Trigger Attack Campaigns Programmatically](https://docs.usetrident.dev/api/red-team.md): Use the Trident Red-Team API to trigger automated attack campaigns, poll for results, and run garak probe suites from your code or CI/CD.
- [Install and Configure the tridentctl CLI for Trident](https://docs.usetrident.dev/cli/installation.md): Install tridentctl to scan your local environment, run promptfoo security evaluations, and verify agent certificates from the command line.
- [tridentctl CLI Command Reference: Flags and Examples](https://docs.usetrident.dev/cli/reference.md): Full reference for all tridentctl commands: init, evals, cert, verify, and jwks — with flags, examples, output format, and CI usage patterns.
- [Find Multi-Hop Cloud Attack Paths Linked to AI Agents](https://docs.usetrident.dev/cloud/attack-paths.md): Trident's toxic combo engine finds multi-hop attack paths connecting AI agent vulnerabilities to sensitive cloud data, ranked by exploitability.
- [Connect Your Cloud Accounts to Trident Cloud Security](https://docs.usetrident.dev/cloud/connecting.md): Connect your AWS, Azure, GCP, or Kubernetes environment to Trident using a read-only IAM role — no agents installed, no network changes required.
- [Cloud Security: Map Assets and Attack Paths for AI](https://docs.usetrident.dev/cloud/overview.md): Trident Cloud continuously maps your cloud infrastructure, surfaces attack paths from AI agents to sensitive data, and prioritizes what to fix first.
- [Remediate Cloud Security Issues with Automated PRs](https://docs.usetrident.dev/cloud/remediation.md): Trident's Sentinel AI generates draft remediation code and opens GitHub pull requests for cloud security findings — you review and merge.
- [LLM Gateway: Route Agent Calls Through Trident](https://docs.usetrident.dev/configuration/gateway.md): The Trident gateway is a drop-in proxy for OpenAI and Anthropic APIs that inspects every prompt and output with the runtime firewall.
- [Manage Trident Projects and API Keys](https://docs.usetrident.dev/configuration/projects.md): Projects are Trident's top-level workspaces. Manage API keys, team members, and project-level settings from the dashboard.
- [Custom Scorers: Evaluate Agent Responses Your Way](https://docs.usetrident.dev/configuration/scorers.md): Write custom JavaScript scorer functions in the Trident dashboard to evaluate agent responses against your own quality and safety criteria.
- [Set Up Signals to Monitor Agent Health](https://docs.usetrident.dev/configuration/signals.md): Signals are no-code threshold monitors that alert you when agent error rates, latency, LLM cost, or finding counts cross a threshold.
- [Trident Core Concepts: Projects, Agents, and Findings](https://docs.usetrident.dev/core-concepts.md): Learn the key concepts behind Trident — projects, agents, traces, findings, the runtime firewall, the cloud security graph, and how they work together.
- [Add AI Agent Security Tests to Your CI/CD Pipeline](https://docs.usetrident.dev/integrations/ci-cd.md): Run Trident red-team evaluations as a pre-deploy gate in GitHub Actions, GitLab CI, or any CI/CD system using the tridentctl CLI.
- [GitHub Integration: Automated Remediation Pull Requests](https://docs.usetrident.dev/integrations/github.md): Connect Trident to GitHub to receive automated draft pull requests for cloud security findings and AI agent vulnerability fixes.
- [Trident Integrations: Connect Your Entire Stack](https://docs.usetrident.dev/integrations/overview.md): Trident integrates with 24+ tools across cloud, identity, data, AI frameworks, security, and DevOps to give you a unified security view.
- [Route Trident Alerts to Slack and PagerDuty](https://docs.usetrident.dev/integrations/slack-pagerduty.md): Send Trident Signal alerts and critical findings to Slack channels or PagerDuty incidents for real-time team notification.
- [Trident — AI Agent Security and Cloud Risk Platform](https://docs.usetrident.dev/introduction.md): Trident gives engineering and security teams observability, automated red-teaming, a runtime firewall, and a cloud security graph for production AI agents.
- [Quickstart: Instrument Your First AI Agent with Trident](https://docs.usetrident.dev/quickstart.md): Install the Trident SDK, initialize it with your project keys, and see your first security traces in the dashboard in under 5 minutes.
- [Install the Trident Python SDK (vouch-sdk)](https://docs.usetrident.dev/sdk/python/installation.md): Install vouch-sdk and instrument Python AI agents, LangChain, CrewAI, and more with Trident observability and security in one call.
- [Python SDK API Reference (vouch-sdk)](https://docs.usetrident.dev/sdk/python/reference.md): Complete API reference for vouch-sdk: vouch_sdk.init(), firewall_headers(), redact_text(), redact_value(), and configuration options.
- [Install the Trident TypeScript SDK](https://docs.usetrident.dev/sdk/typescript/installation.md): Install @vouch-ai/sdk to auto-trace LLM calls in your Node.js agent. One init() instruments OpenAI, Anthropic, LangChain, and Bedrock.
- [TypeScript SDK API Reference (@vouch-ai/sdk)](https://docs.usetrident.dev/sdk/typescript/reference.md): Complete API reference for the @vouch-ai/sdk package: trident.init(), trident.scan(), trident.selfReport(), and configuration options.