Where AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden Vulnerabilities

Summary

Knostic researchers examined how LLM-based vulnerability discovery harnesses can miss real, reachable flaws because of their surrounding code, such as file selection, filtering, and result merging. Starting from their own OpenAnt and raptor harnesses and 10 other open-source harnesses, they mapped 13 points where findings get dropped and organized them into a taxonomy. In six harnesses, a single file was dropped before the model saw it, five of them silently.

Related items

• InfoIs Claude Code safe for the enterprise? What the official settings cover, and what they don'tSimilar attack · Adversa AI Blog
• Info‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake TargetsSimilar attack · SecurityWeek
• InfoPrompt Injection Through Forensic Evidence: A Taxonomy and Proof of Concept of Anti-Forensic Attacks on LLM-Assisted Digital InvestigationsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoThe Harness Is the Hard Part of Agentic PentestingSimilar attack · The Hacker News
• InfoA Unified Evaluation Framework of Physical Adversarial Robustness in the Edge VLM EraSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)