Skip to main content
Search

# Vulnerability Discovery

6 related articles

Subscribe to updates
  1. Cohere Labs

    Cohere closes AISLE acquisition and brings in cubic's team, folding autonomous vulnerability discovery and code review into its sovereign AI platform

    Cohere said it has completed its acquisition of AISLE, a company building autonomous systems for vulnerability discovery and remediation, and has welcomed the team behind cubic, an AI-powered code review platform; the two are to form the foundation of Cohere Cyber, its cybersecurity business, and of a secure coding vertical. Cohere had already acquired Aleph Alpha and Reliant AI, and says these two additions bring its strategic M&A transactions this year to four. AISLE's co-founders take leadership roles in cybersecurity, corporate security and AI security research, and Cohere plans a substantial long-term investment in Prague as its global center for AI cybersecurity and autonomous security systems.

  2. OpenAI News

    GPT‑6 Cyber ships with ExploitGym at 48.5%, up from 32.1%, and 99.93% avoidance of out-of-scope exploitation

    OpenAI released GPT‑6 Cyber for security research, scoring 48.5% on ExploitGym, which tests whether a model can exploit a specified vulnerability, up from 32.1% for GPT‑5.6 Cyber. In a separate alignment evaluation, the model avoided exploiting out-of-scope services in 99.93% of tests without its deployment prompt, versus 94.49% for GPT‑5.6 Cyber, and reached 100% with the prompt. OpenAI says it has been used to develop 948 privilege escalation exploits in Linux and to find 81 previously unknown high-severity vulnerabilities in Firefox.

  3. Cloudflare splits vulnerability hunting into six stages: an open audit skill where hunters, verifiers and records stay separate

    Cloudflare has published a coding-agent skill that runs a security audit in six phases: reconnaissance, coverage-led hunting, candidate validation, structured output, independent record verification and target-neutral reporting. It is the single-repo starting point from which Cloudflare's vulnerability discovery harness evolved, requires that the agent checking a finding is never the one that found it, and sorts results into confirmed, needs-validation and rejected records. Repeated runs against the same repository are additive, using prior ledgers to target gaps and revalidate changed source.

  4. arXiv

    Tool descriptions become security contracts: 253 bugs in 273 MCP servers, most without a crash

    When a large language model calls an external tool, the orchestration layer checks that the call is well formed, not that its arguments are safe. ToFu turns the argument semantics already documented in tool metadata into executable security checks, then generates fuzzing inputs and oracles from them, confirming 253 bugs across 343 tools in 118 of 273 runnable MCP servers, most of which returned normally.

  5. arXiv

    AVRI Cuts Vulnerability-Discovery Cost by 18.0% for Codex and 23.7% for OpenCode via a Persistent Bidirectional Evidence Trace

    A multi-axis open-coding study of 200 CyberGym traces found that code localization and understanding (43.1%) plus vulnerability reasoning and trigger design (17.3%) account for 60.4% of tokens and that only 24.4% of matched comparisons preserve success at lower total cost; the authors then present AVRI, an interface built on a persistent Bidirectional Evidence Trace (BET), which on 20 evaluation tasks reduces total cost by 18.0% for Codex and 23.7% for OpenCode while preserving success and improving or maintaining recall.

  6. arXiv

    ASPIRE uses a behavior graph and dual explore-exploit experts to find agent prompt-injection vulnerabilities, reaching 54.1% attack success on AgentDojo

    ASPIRE is an open-ended prompt-injection red-teaming framework for LLM agents that maintains an evolving Agent Security Behavior Graph, uses complementary Explore and Exploit experts to propose consequence-centric test skeletons, has a separate realizer build concrete payloads and trigger queries, and updates the graph and cross-run strategy memory from trajectory evidence; on AgentDojo and AgentDyn it raises attack success to as high as 54.1% while covering more consequences, injection methods, environments, and behavior paths.

You’re all caught up