New from Knostic Research: Where AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden Vulnerabilities

AI vulnerability discovery harnesses can miss real, reachable vulnerabilities because of how the surrounding software is built, and how potentially, this can also be used by an attacker to hide vulnerabilities in plain sight.

This study began while hardening two harnesses I help maintain, Knostic's own OpenAnt, and raptor. We then conducted an exploratory survey by feeding known vulnerabilities to harnesses, analyzed the root causes of the misses, and used the data to run a cross-sectional survey of 10 other harnesses.

The paper aims to share these findings with the community and, hopefully, spark a broader discussion of the engineering challenges and threats involved with harness engineering, in cyber security, and beyond.

A common pattern is that descriptive rules become prescriptive. Assumptions about typical file extensions, function names, entry points, or model responses become filters that determine what gets analyzed.

This is similar to work such as from Thomas Ptacek and Timothy Newsham's "Insertion, Evasion, and Denial of Service: Eluding Network Intrusion Detection", all the way back in 1998.

Blog:
https://www.knostic.ai/blog/where-ai-vulnerability-scanners-go-quiet

Link to paper:
https://arxiv.org/abs/2610.29379