"No path found" is the most useful thing a security agent can say.
Building Blastradius for Graph Hacks with FalkorDB Live demo: https://13-203-50-195.sslip.io · Code: https://github.com/NishaadG/blastradius Every time a new CVE lands, someone asks the same four questions: Are we affected? Through which dependency? Who owns that service? Did we already deal with something like this? Most tools answer with a list. The honest answer is a path . The problem with…
For every new cybersecurity vulnerability, the same four questions pop up: Are we affected? Through which dependency? Who owns that service? Did we already deal with something like this? Traditional tools often provide a list of results, but this approach is unsuitable for answering critical questions about connections. Blastradius, a graph-based security tool, offers a more effective solution by utilizing graph traversals to answer these questions in a matter of milliseconds.
By querying a graph of services, packages, and dependencies, Blastradius can quickly determine the exact chain of affected services, the responsible team, and the fixed version, all while providing evidence of the absence of connections when relevant. Blastradius leverages a graph database, FalkorDB, to store ownership, memory, and dependency data in a single structure, enabling efficient querying and eliminating the need for manual handoffs.
The tool uses plain rules and graph evidence to determine whether a vulnerability affects a specific service or not, with the LLM only deciding which tool to call and phrasing the results. The tool is also capable of discovering dependencies from project deployment files, Kubernetes manifests, and Compose files, ensuring comprehensive coverage of potential vulnerabilities.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.