arXiv:2607. 26314v1 Announce Type: cross Abstract: Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones.
arXiv:2608. 09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.
arXiv:2607. 26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.
arXiv:2607. 15263v1 Announce Type: cross Abstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion.
arXiv:2606. 14295v1 Announce Type: cross Abstract: Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation.
arXiv:2606. 13994v1 Announce Type: cross Abstract: LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world.
arXiv:2607. 01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks.
arXiv:2607. 07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not.
arXiv:2606. 13079v1 Announce Type: cross Abstract: Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross.
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
HarnessRisk is a lifecycle-oriented benchmark for evaluating safety in agent harnesses that manage tools, extensions, state, permissions, and external actions. It defines six operational phases—Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery—and includes 128 sandboxed cases pairing benign user objectives with adversarial instructions. Across three harnesses, six language models, and 14 configurations, attack success rates vary from 12.6% to 80.9%, with the most vulnerable phase being Harness Configuration. "whyItMatters":"The benchmark demonstrates that safety failures can arise in multiple harness responsibilities and that even explicit risk detection does not guarantee safe action, underscoring the need for comprehensive evaluation across model and harness configurations."
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
The paper introduces CTF-ABACUS, a trace-based auditing framework that reconstructs each autonomous language-model agent’s run in Capture-the-Flag (CTF) challenges into evidence‑grounded solve profiles. By decomposing actions into penetration‑testing phases and techniques, it distinguishes genuine exploitation from shortcut methods such as memorized recall or guessing. Applying the framework to 1,435 CTF attempts by six models on 240 challenges shows that only 62‑87% of recovered flags are trace‑verified, highlighting that many successes rely on shallow trajectories rather than true exploitation.