The paper evaluates CASCADE, a fully local layered defense for Model Context Protocol (MCP)-based systems, by conducting a component ablation and corpus audit on a fixed 5,000-sample dataset. It demonstrates that the choice of aggregation convention heavily influences reported metrics, that detection performance varies with provenance, and that the released configuration does not fully disclose the operating point. The study also shows that a local review model invoked for a third of requests does not alter classification outcomes, highlighting the importance of reproducibility and transparency in defense evaluations.
arXiv:2605. 28734v2 Announce Type: replace-cross Abstract: A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written.
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
TriShieldRAG introduces a three‑layered defense for Retrieval‑Augmented Generation: an Ingest Guard that screens documents, a Retrieval Scorer that re‑ranks based on trust, and a Cross‑LLM Consensus that validates evidence across three models. Against the original PoisonedRAG attack on the 2.68M‑passage Natural Questions corpus, the framework reduces attack success from about 79% to 1%. However, adaptive attacks that only alter document formatting can bypass the Ingest Guard and still achieve high success rates, revealing limits of layered defenses that rely on the same retrieved evidence.
The paper audits the reproducibility of knowledge‑graph extraction from threat reports by re‑implementing matching rules for only five of twelve systems and re‑scoring ten system outputs under eight protocols. The audit shows that different matching protocols can reverse most pairwise system rankings and that a fixed prediction set can vary from 0.16 to 0.70 F1. The authors also build CTIForge to isolate validation effects, finding that validation changes precision across backbones and increases entity‑type disputes, and they release the full pipeline, protocol suite, and audit records.
The paper introduces a new taxonomy for benchmark contamination that categorizes leakage by the mitigation it defeats—direct, derivative, temporal, distributional, and acquired—covering both training‑time and evaluation‑time scenarios. It proposes a four‑field disclosure protocol to record contamination status alongside benchmark scores, and provides a JSON schema, validator, and examples. An empirical study of 41 documents using a pre‑registered instrument shows limited reporting of contamination types and variable reliability, highlighting gaps in current disclosure practices.
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.
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:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
arXiv:2608. 12880v1 Announce Type: cross Abstract: Security evaluations of tool-using agents often equate stored labels with behavioral facts.
ClawSentry is an open‑source, framework‑agnostic security supervision gateway designed to protect autonomous large language model (LLM) agents from progressive risks that can arise at four points in the agent control loop: skill admission, invocation‑time intent, execution‑time effect, and post‑action consequence. It introduces a multi‑tier decision engine—deterministic L1, rule‑anchored L2, and read‑only L3—alongside a First‑Use Skill Package Review (FSPR) and an Agent Harness Protocol (AHP) that applies a single policy across multiple agent runtimes without modifying their internals. Evaluation on SkillInject and the SkillsSafety benchmark shows that ClawSentry significantly reduces contextual adversarial skill risk (ASR) while maintaining high task success rates (TSR).
arXiv:2607. 09691v1 Announce Type: cross Abstract: A modern coding agent can hold an entire repository in its context window.