shannon vs ai-infra-guard
Two of the top projects in Security, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
shannon
Autonomous pentester that exploits web apps and APIs using source analysis
ai-infra-guard
Red-teaming platform for AI infra CVEs, MCP servers, agent skills and jailbreaks
Verdict
shannon ranks higher, 92 to 79. Of the 4 score parts we measure for both, shannon leads on 1, ai-infra-guard on 1 and 2 are even.
- Adoptionshannon leads by 47 points, 94 to 47: a wide gap.
- FreshnessEven at 100.
- MaintenanceEven at 93.
- Agent-readyai-infra-guard leads by 15 points, 70 to 55: a wide gap.
Pick shannon if you are
Developers and small security teams pentesting their own apps in staging or CI
- Reports only exploits with a reproducible proof of concept, which cuts speculative findings
- Outputs PDF, Markdown, JSON and SARIF 2.1.0, with GitHub and GitLab CI integrations
Pick ai-infra-guard if you are
Security teams auditing self-hosted AI services, MCP servers and agent skills
- Fingerprints 100+ AI components (Ollama, vLLM, ComfyUI, n8n, Triton) against 2000+ CVE rules
- Covers infra CVEs, MCP and skill scanning, and jailbreak evaluation in one web UI
| What we compare | shannon | ai-infra-guard |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 94, widely used | 47, known |
| Freshness | 100, active | 100, active |
| Maintenance | 93, healthy | 93, healthy |
| Agent-ready | 55, partly | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 51.8k | 7.5k |
| License | AGPL-3.0 (copyleft) | Apache-2.0 (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | TypeScript | Python |
| Docker | Yes | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
shannon
Shannon reads a target app's source, builds a queue of candidate attack paths, then uses browser automation and CLI tools to try real exploits against the running app. Only findings with a working proof of concept reach the PDF, Markdown, JSON or SARIF 2.1.0 report. It runs from an npx launcher with a Docker worker, and has GitHub Actions and GitLab CI components that can fail a pipeline on exploited vulnerabilities.
Who it is for: Developers and small security teams pentesting their own apps in staging or CI
Strengths
- Reports only exploits with a reproducible proof of concept, which cuts speculative findings
- Outputs PDF, Markdown, JSON and SARIF 2.1.0, with GitHub and GitLab CI integrations
- Bring your own key: Anthropic, OpenAI, xAI, Bedrock, gateways, or local Ollama, vLLM, LM Studio
- Supports authenticated scans (login flows, TOTP) and resumable workspaces
Weaknesses
- Needs the target's source code; black-box testing is only in paid editions
- Actively executes exploits, so it must not be run against production
- Covers injection, XSS, SSRF, authentication and authorization only
- Claude Code subscriptions unsupported after version 1.9.0; AGPL-3.0 license
- no GPU
- Docker + Compose
- Needs Docker, Node.js 22+, LLM provider credentials
- Models: Anthropic, OpenAI, xAI, AWS Bedrock, Ollama
ai-infra-guard
A.I.G (AI-Infra-Guard) from Tencent Zhuque Lab is a web platform that fingerprints running AI services such as Ollama, vLLM, ComfyUI and n8n against 2000+ CVE rules. It also scans MCP servers and agent skills from source or URL, runs jailbreak evaluations against a target LLM API, and includes a model and API relay checker. Standalone CLIs exist for skill, MCP and agent scanning.
Who it is for: Security teams auditing self-hosted AI services, MCP servers and agent skills
Strengths
- Fingerprints 100+ AI components (Ollama, vLLM, ComfyUI, n8n, Triton) against 2000+ CVE rules
- Covers infra CVEs, MCP and skill scanning, and jailbreak evaluation in one web UI
- Separate CLIs such as pip-installable aig-skill-scan fit into CI/CD pipelines
- Rules are YAML files under data/, so contributing fingerprints is straightforward
Weaknesses
- No authentication; README says not to deploy on public networks
- Skill scanning needs an external LLM API key
- Online Pro version with extra features requires an invitation code
- API checker from source needs a Python venv and a Go build
- RAM ≥ 4 GB
- no GPU
- Docker + Compose
- Needs Docker 20.10+, LLM API key for skill, MCP and jailbreak scans
- Models: OpenAI-compatible LLM APIs (base URL + key)
- port 8088
More in Security
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.