Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems

• URL: http://arxiv.org/abs/2605.11891v1
• Date: Tue, 12 May 2026 10:05:54 GMT
• Title: Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems
• Abstract summary: Agent skills expose both executable behavior and context-setting documentation.<n>A realistic attacker can use audit and runtime feedback to repeatedly rewrite the skill.<n>Proteus searches a formalized five-axis skill-attack space.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both executable behavior and context-setting documentation, its deployment risk cannot be measured by single-shot audits or prompt-level red teams alone: a realistic attacker can use audit and runtime feedback to repeatedly rewrite the skill. We frame this risk as \emph{adaptive leakage} -- whether a budgeted attacker can iteratively revise a skill until it passes audit and produces verified runtime harm -- and present \ours{}, a grey-box self-evolving red-team framework for measuring it. Proteus searches a formalized five-axis skill-attack space. Each candidate is evaluated through a unified audit-sandbox-oracle pipeline that returns structured audit findings and runtime evidence to guide cross-round mutation. Beyond initial evasion, Proteus performs path expansion, which finds alternative implementations of successful attacks, and surface expansion, which transfers learned implementation patterns to new attack objectives beyond the original seed catalogue. Across eight phase-1 cells, Proteus reaches 40--90\% Attack Success Rate at $5$ rounds (ASR@5) with positive learning-curve slopes on both evaluated auditors. Phase-2 path/surface expansion produces 438 jointly bypassing and lethal variants, with SkillVetter bypassed at $\geq 93\%$ in every cell and AI-Infra-Guard, the strongest public auditor we evaluate, still admitting up to 41.3\% joint-success. These results show that current skill vetting substantially underestimates residual risk when evaluated against adaptive, feedback-driven attackers.

Related papers

• Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents [30.77975669386977]
  We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill.<n>Our guard, SkillSonar, checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision.
  arXiv  Detail & Related papers  (2026-09-01T16:19:31Z)
• SIR: Self-improving Red-teaming for Compute Use Agents [71.71987044117371]
  Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal.<n>Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI)<n>We present SIR, a black box IPI attack that composes stealthy injections from a small library of reusable principles stated in plain language.
  arXiv  Detail & Related papers  (2026-08-31T03:39:43Z)
• AgentWorld: Personality-Aware Reliability Evaluation for Agentic Information Retrieval [1.1647715835517187]
  AgentWorld is a simulation framework combining personality-driven user populations with stateful tool-use environments.<n>Three experiments demonstrate the framework: a conversational analytics agent across 10 OCEAN personas (240 evaluator judgments); a customer-support agent across 5 tasks $times$ 4 persona variants; and adversarial stress-testing of 5 tasks revealing pre-existing trajectory brittleness.
  arXiv  Detail & Related papers  (2026-08-25T05:15:33Z)
• Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle [65.6642776933861]
  This survey examines the protective paradigm that has grown around this intervention point.<n>We find that most protections are still validated mainly against static or weakly adaptive adversaries.<n>We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.
  arXiv  Detail & Related papers  (2026-08-05T00:46:50Z)
• Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines [34.37967130277969]
  We propose a two-agent evasion framework operating in a semantic perturbation space.<n>Evasion rates are 19.95 to 40.34% on modern large language model (LLM) based systems.<n>A pattern-informed defense reduces the evasion rate by up to 65.18%.
  arXiv  Detail & Related papers  (2026-04-26T00:58:36Z)
• SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement [66.44008181092832]
  LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities.<n>We introduce SkillAttack, a framework that verifies skill vulnerability exploitability through adversarial prompting.
  arXiv  Detail & Related papers  (2026-04-05T06:25:11Z)
• Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems [35.65937852381774]
  Document-Driven Implicit Payload Execution (DDIPE) embeds malicious logic in code examples and configuration templates within skill documentation.<n>We generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories.<n>DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses.
  arXiv  Detail & Related papers  (2026-04-03T14:58:58Z)
• Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions [2.0415910628419067]
  We propose profit-driven red teaming, a stress-testing protocol that replaces handcrafted attacks with a learned opponent trained to maximize its profit.<n>We instantiate it in a lean arena of four canonical economic interactions, which provide a controlled testbed for adaptive exploitability.<n>We distill exploit episodes into concise prompt rules for the agent, which make most previously observed failures ineffective and substantially improve target performance.
  arXiv  Detail & Related papers  (2026-03-21T19:56:54Z)
• Measuring and Exploiting Confirmation Bias in LLM-Assisted Security Code Review [6.417595678110472]
  We study whether confirmation bias affects LLM-based vulnerability detection, and whether this failure mode can be exploited in software supply-chain attacks.<n>Study 1 quantifies confirmation bias through controlled experiments on 250 CVE vulnerability/patch pairs evaluated across four state-of-the-art models under five framing conditions for the review prompt.<n>Study 2 evaluates exploitability in practice mimicking adversarial pull requests that reintroduce known vulnerabilities while framed as security improvements or urgent functionality fixes via their pull request metadata.
  arXiv  Detail & Related papers  (2026-03-19T10:40:27Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification [71.98473277917962]
  Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving.<n>We propose an alternative paradigm: self-evolving the agent's ability by iteratively verifying the policy model's outputs, guided by meticulously crafted rubrics.<n>We present DeepVerifier, a rubrics-based outcome reward verifier that leverages the asymmetry of verification.
  arXiv  Detail & Related papers  (2026-01-22T09:47:31Z)
• AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications [71.27518152526686]
  Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation.<n>LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task.<n>This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types.
  arXiv  Detail & Related papers  (2025-12-23T08:42:09Z)
• Quantifying Return on Security Controls in LLM Systems [0.0]
  This paper introduces a decision-oriented framework to quantify residual risk.<n>It converts adversarial probe outcomes into financial risk estimates and return-on-control metrics.
  arXiv  Detail & Related papers  (2025-12-17T04:58:09Z)
• Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models [75.29749026964154]
  Ourmethod reduces the average Attack Success Rate to 4.41% across multiple benchmarks.<n>Clean accuracy and utility are preserved within 0.5% of the original model.<n>The defense generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.
  arXiv  Detail & Related papers  (2025-10-11T15:47:35Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.