AI-SPM vs Shannon

AI-SPM (AI Security Posture Management) is an open-source infrastructure layer for securing LLM pipelines running in production. It targets three attack surfaces that traditional application security doesn't cover: prompt injection (including obfuscated and multi-step variants), tool abuse via unvalidated structured outputs, and data exfiltration through PII leakage in model responses. The architecture layers a gateway intercept layer over incoming prompts, runs context inspection before the LLM sees any input, enforces policies via Open Policy Agent (OPA) for declarative, auditable rules, then pipes all events through Apache Kafka and Apache Flink for real-time streaming analysis. This means security posture can be monitored and enforced at scale without blocking the inference path. The project is genuinely fresh — posted as a Show HN today. Early community feedback pointed to capability-based token models (similar to OS kernel permission rings) as a complementary approach to content-scanning, which the author acknowledged as a meaningful gap. The timing is right: as companies push AI agents from demos to production, the security tooling layer is largely underdeveloped. AI-SPM is one of the first OSS projects to tackle it at the infrastructure layer rather than with prompt-level guardrails alone.

Shannon is an autonomous AI security research agent from Keygraph that takes a target (web app, API, or codebase) and runs a full offensive security workflow: static analysis, attack surface mapping across OWASP Top 10, and then actual proof-of-concept exploit execution — all without manual intervention. It orchestrates real security tools (Nmap, Subfinder, SQLMap, Playwright) under the hood, not just generating reports. The Lite tier (AGPL-3.0) handles web apps and API endpoints, running browser automation and fuzzing attacks autonomously. Shannon Pro (commercial) adds SAST/SCA integration, CI/CD pipeline hooks for PR scanning, and team-level finding management. The model layer is pluggable — defaults to GPT-4o for planning with Claude Sonnet for exploit reasoning, but can be pointed at local models. What sets Shannon apart from tools like Burp Suite or ZAP is the agentic loop: it doesn't just surface a list of potential issues, it attempts exploitation and logs what worked. For small security teams and solo founders doing pre-launch security checks, this compresses days of pentesting work into a single automated run. The open-source Lite tier is the real news here — genuine autonomous exploitation capability, freely available.