Build secure AI agents from the start. Scan for logic bugs, prompt injection, missing guardrails, and compliance gaps — before they reach production.
English · 简体中文 · 日本語 · 한국어 · Español · Português · Deutsch · Français
AI agents can loop forever, drain your API budget in minutes, execute arbitrary code from user input, or make high-stakes decisions with zero human oversight. Most of these flaws pass code review because they look like normal code — the danger is in the runtime behavior.
Inkog scans your agent code statically and catches these problems before deployment. One command, works across 21 frameworks, maps findings to EU AI Act and OWASP LLM Top 10.
Want to try it without installing anything? Drop a repo URL into the free scanner at inkog.io — no signup required.
- Deep scan (
inkog -deep) — orchestrator-driven analysis that catches subtle logic flaws pattern matching misses - Skill & MCP scanning — audit
SKILL.mdpackages and MCP servers for tool poisoning, command injection, excessive permissions - MLBOM generation — Machine Learning Bill of Materials for your agent
- AG2 + Azure AI Foundry support
- AI provider secret detection — Anthropic, Gemini, Groq, HuggingFace
- CI/CD templates — GitLab CI, Azure DevOps, Jenkins (alongside the existing GitHub Action)
See the full CHANGELOG.
- Building an AI agent — Scan during development to catch infinite loops, prompt injection, and missing guardrails before they ship
- Adding security to CI/CD — Add
inkog-io/inkog@v1to GitHub Actions for automated security gates on every PR - Preparing for EU AI Act — Generate compliance reports mapping your agent to Article 14, NIST AI RMF, OWASP LLM Top 10
- Reviewing agent code — Use from Claude Code, Cursor, or any MCP client to get security analysis while you code
- Auditing MCP servers — Check any MCP server for tool poisoning, privilege escalation, or data exfiltration before installing
- Verifying AGENTS.md — Validate that governance declarations match actual code behavior
- Scanning Skill packages — Audit SKILL.md packages for tool poisoning, command injection, and excessive permissions before adding to your agent
- Generating an MLBOM — Create a Machine Learning Bill of Materials documenting your agent's components, tools, and data flows
- Building multi-agent systems — Detect delegation loops, privilege escalation, and unauthorized handoffs between agents (A2A audit)
Try it on a repo from your browser — inkog.io/scan. No signup, no install.
For local scans, no install needed:
npx -y @inkog-io/cli scan .Or install permanently:
| Method | Command |
|---|---|
| Install script | curl -fsSL https://inkog.io/install.sh | sh |
| Homebrew | brew tap inkog-io/inkog && brew install inkog |
| Go | go install github.com/inkog-io/inkog/cmd/inkog@latest |
| Binary | Download from Releases |
# Get your free API key at https://app.inkog.io
export INKOG_API_KEY=sk_live_...
inkog .| Category | Examples | Why it matters |
|---|---|---|
| Infinite loops | Agent re-calls itself with no exit condition, LLM output fed back as input without a cap | Your agent runs forever and racks up API costs |
| Prompt injection | User input flows into system prompt unsanitized, tainted data reaches tool calls | Attackers can hijack your agent's behavior |
| Missing guardrails | No human-in-the-loop for destructive actions, no rate limits on LLM calls, unconstrained tool access | One bad decision and your agent goes rogue |
| Hardcoded secrets | API keys, tokens, and passwords in source code (detected locally, never uploaded) | Credentials leak when you push to GitHub |
| Compliance gaps | Missing human oversight (EU AI Act Article 14), no audit logging, missing authorization checks | You're legally required to have these controls by August 2026 |
Code-first: LangChain · LangGraph · CrewAI · AutoGen · AG2 · OpenAI Agents · Semantic Kernel · Azure AI Foundry · LlamaIndex · Haystack · DSPy · Phidata · Smolagents · PydanticAI · Google ADK
No-code: n8n · Flowise · Langflow · Dify · Microsoft Copilot Studio · Salesforce Agentforce
- uses: inkog-io/inkog@v1
with:
api-key: ${{ secrets.INKOG_API_KEY }}
sarif-upload: true # Shows findings in GitHub Security tabFull CI/CD docs → | Complete workflow example →
Deep scan
Run an advanced orchestrator-based analysis with enriched findings, an agent profile, compliance coverage, and a premium HTML report:
inkog -deep .
inkog -deep -output html . > deep-report.htmlRequires the Inkog Deep role. Deep scan docs →
Skill & MCP scan
Scan SKILL.md packages, agent tools, and MCP servers for vulnerabilities:
# Scan a skill package
inkog skill-scan .
inkog skill-scan --repo https://github.com/org/repo
# Scan an MCP server by registry name
inkog mcp-scan github
inkog mcp-scan github --repo https://github.com/org/mcp-server
# Deep scan either
inkog skill-scan --deep .
inkog mcp-scan --deep --repo https://github.com/org/mcp-serverScan policies
inkog . --policy low-noise # Only proven vulnerabilities
inkog . --policy balanced # Vulnerabilities + risk patterns (default)
inkog . --policy comprehensive # Everything including hardening tips
inkog . --policy governance # Article 14 controls, authorization, audit trails
inkog . --policy eu-ai-act # EU AI Act compliance reportScan agent code directly from Claude, ChatGPT, or Cursor:
npx -y @inkog-io/mcp7 tools including MCP server auditing, Skill package scanning, and multi-agent topology analysis. MCP docs →
Automated adversarial testing for AI agents. Inkog Red probes your running agents with prompt injection, jailbreaks, and tool misuse attacks to validate that defenses hold under real-world conditions.
- Documentation — CLI reference, detection patterns, integrations
- Slack — Questions, feedback, feature requests
- Issues — Bug reports and feature requests
- Contributing — We welcome PRs
- Changelog — Release history
Apache 2.0 — See LICENSE