AI-SPM
Open-source runtime security control plane for LLM agents in production
The Panel's Take
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.
Share this verdict
AI-SPM verdict: SKIP ⏭️ 2 ships · 2 skips from the expert panel Full review: shiporskip.io/tool/ai-spm-runtime-security-ai-agents-opa-kafka-flink-open-source-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare AI-SPM with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/ai-spm-runtime-security-ai-agents-opa-kafka-flink-open-source-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/ai-spm-runtime-security-ai-agents-opa-kafka-flink-open-source-2026" alt="AI-SPM Skip verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/ai-spm-runtime-security-ai-agents-opa-kafka-flink-open-source-2026)<iframe src="https://shiporskip.io/embed/ai-spm-runtime-security-ai-agents-opa-kafka-flink-open-source-2026" title="AI-SPM ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“OPA for policy enforcement means you can write Rego rules that your compliance team can audit — that's actually deployable in enterprise contexts. The Kafka/Flink pipeline is heavy infrastructure overhead for small teams, but for anyone running production agents at scale, this is addressing a real gap.”
“Content scanning for prompt injection is a cat-and-mouse game — adversarial prompts can be obfuscated faster than pattern libraries can be updated. The Kafka + Flink dependency stack is substantial for a project that just launched today with no production deployments documented. Wait for community hardening.”
“Agent security is the next frontier of the AI stack and it's almost entirely unsolved today. AI-SPM's framing — treat AI agents like network services with a dedicated security control plane — is the right mental model. This category will matter enormously as agents get production write access to real systems.”
“The GitHub repo is technically solid but documentation is still thin for anyone who isn't already comfortable with OPA and Kafka. Not a problem for security engineers, but the broader AI developer audience building agents will find it hard to evaluate what they're actually getting before investing in the stack.”