Can We Trust AI To Write Vulnerability Checks? Here's What We Found

Intruder describes how its security team uses an agentic AI approach (via Cursor) to speed up creation of reliable Nuclei vulnerability checks—particularly for exposed admin panels and unsecured Elasticsearch—by combining curated examples, rules, and human oversight; the post details their workflow, productivity gains, and current challenges (like weak matchers, truncated curl output, and overlooking Nuclei flags), concluding that AI is a valuable accelerator but not a replacement for expert engineers.