Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag risk but recover malicious intent inconsistently under semantics-preserving rewrites. This paper formulates pre-load auditing for untrusted Agent Skills as a robust three-way classification task and introduces SkillGuard-Robust, which combines role-aware evidence extraction, selective semantic verification, and consistency-preserving adjudication. We evaluate SkillGuard-Robust on SkillGuardBench and two public-ecosystem extensions through five large evaluation views ranging from 254 to 404 packages. On the 404-package held-out aggregate, SkillGuard-Robust reaches 97.30% overall exact match, 98.33% malicious-risk recall, and 98.89% attack exact consistency. On the 254-package external-ecosystem view, it reaches 99.66%, 100.00%, and 100.00%, respectively. These results support a bounded conclusion: factorized package auditing materially improves frozen and public-ecosystem robustness, while harsher external-source transfer remains an open challenge.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors
Genomic Foundation Models (GFMs), such as Evolutionary Scale Modeling (ESM), have demonstrated remarkable success in variant effect prediction. However, their security and robustness under adversarial manipulation remain…
Agent Audit: A Security Analysis System for LLM Agent Applications
What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone…
Adaptive Plan-Execute Framework for Smart Contract Security Auditing
Large Language Models (LLMs) have shown great promise in code analysis and auditing; however, they still struggle with hallucinations and limited context-aware reasoning. We introduce SmartAuditFlow, a novel Plan-Execute…
RAGRetrieval-augmented GenerationVulnerability DetectionPrivacy Enhancement for Cloud-Based Few-Shot Learning
Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains. However, deploying few-shot models in untrusted environments may inflict privacy concerns, e.g.,…
Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage ClassificationUntrusted Content Masking for Web Agents with Security Guarantees
Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such as tool-use APIs, this separation arise…