arXiv AI
Capability-Gated Language Models: Security Composes, Utility Does Not
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 1
Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection
arXiv:2608.30041v1 Announce Type: cross Abstract: Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later pri...
arXiv AI
Sep 25
Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery
The paper introduces skilder, a framework that organizes LLM agent capabilities into role‑scoped bundles of skills, tools, and instructions, with explicit limits. Agents start with a minimal role catalog, discover the roles needed for a task, and receive the associated tools only through a single MCP server, ensuring deterministic enforcement of scope. Experiments on 13 tasks with six models show that skilder’s authorization layer prevents unauthorized tool calls and parameter violations while maintaining flexibility through dynamic cross‑role capability acquisition.
arXiv AI
Jun 16
FORTIS: Benchmarking Over-Privilege in Agent Skills
arXiv:2605. 09163v3 Announce Type: replace Abstract: Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution.
arXiv AI
Jul 31
The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
arXiv AI
Oct 9
Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
The paper introduces Dynamic Boundary Evaluation (DBE), a method that moves beyond static benchmarks by locating the per‑prompt pass probability near 0.5 for large language models. DBE provides a calibrated item bank with difficulty labels, a Skill‑Guided Boundary Search algorithm that works with API‑level access, and an adaptive evaluation protocol that places new models on a unified ability scale. The approach is applied to safety, capability, and truthfulness tasks, expanding coverage without saturation and remaining compatible with existing datasets.
arXiv AI
Jul 28
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
arXiv:2607. 24343v1 Announce Type: cross Abstract: Language-model agents act through structured tool calls whose arguments carry different risks.