ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?

Abstract: Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a client's engagement boundary. Existing offensive-security benchmarks measure raw hacking capability; as those benchmarks saturate, the real barrier to deployment is a special case of alignment: scope adherence. We introduce ScopeBench, a benchmark of 30 dead-end agentic security tasks in which the stated objective is reachable only by violating the stated scope. Each task appears under two conditions that share an environment, verifier, and objective and differ only in scope: one instruction set has no scope and measures capability; the other has a natural-language scope to measure adherence. Scopeless trajectories are graded by a standard deterministic verifier. Scoped trajectories pass through two grading arms. First, the same deterministic verifier checks for the flag: because the flag sits behind the scope boundary, a pass proves by construction that a forbidden action occurred, yielding a high-precision lower bound on the violation rate. If the verifier does not pass the trajectory, an agentic judge estimates whether an out-of-scope call occurred. We calibrate the judge against 100 ScopeBench trajectories labeled call-by-call by human annotators, and a blinded audit of the evaluated rollouts finds its high recall holds - no false negatives among the 36 audited violations, with over-flagging its only observed error. Across 8 models in one harness, raw capability spans 12.2% to 81.1% and scope adherence spans 34.4% to 86.7%, with the judge finding 331 violations that mechanical verification misses. Opus-4-8 achieves a raw-capability score 10 percentage points higher than sonnet-4-6's while exhibiting 35.6 percentage points higher scope adherence. We release the frozen pilot benchmark, evaluation code, and all 2160 ATIF trajectories.
Submission history
Access Paper:

Current browse context:
References & Citations
BibTeX formatted citation


arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Verified source · arXiv.org
Reported by arXiv.org. Open the original for full media and formatting.
More in Research
All newsPredicting Transmembrane Protein Topology from 3D Structure
This paper presents a novel approach to infer protein topology using the state-of-the-art graph neural network (GNN), SchNet. The model is trained on the same dataset used to develop the recent DeepTMHMM model with 5-fold cross-validation. Unlike the conventional approaches based on using only the protein sequences or the $α$-carbons as features, we have decoded our classifier in this way, so all atom-level embeddings are used. Without applying any pre-trained weight, the final results have shown great potential that GNNs can be used for topological predictions.
Read at arXiv cs.AIWhen Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess
When one language model judges whether another's code is correct, it does not report the absence of evidence. It returns a confident verdict with reasoning attached, indistinguishable from a verdict it had grounds for. Multi-agent verification, which decomposes a judgment into checkable claims and verifies each against evidence, is a promising response and works well when the evidence is a set of retrieved documents. We argue such methods require two things of their evidence: it must be independent of the answer under review, and it must differ between the two candidates being compared. The s…
Read at arXiv cs.AIStealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a specific task. Skill-based agent systems therefore enable flexible reuse of third-party capabilities, but the openness of this skill ecosystem also opens up a new attack surface. Prior work has focused on vulnerabilities within individual skills, but little attention has been paid to risks that arise from interactions across skills. In this paper, we introduce skill cascading attacks, a threat paradigm in which a maliciou…
Read at arXiv cs.AIBringing AI to Autonomous Systems -- From Cognition to Collective Intelligence
The purpose of this article is to highlight the central role of autonomous systems as the ultimate stage in the development of AI, to explain the underlying technical challenges that require a combination of connectionist AI and symbolic AI, and to integrate AI and systems engineering. We present a comprehensive framework for the design and evaluation of autonomous systems, based on a generic agent architecture that characterizes their behavior as the composition of cognitive functions organized around a long-term memory containing the agent's evolving knowledge. We address the challenges pos…
Read at arXiv cs.AI