MetaCascade: End-to-End Attacks on Agent Skills via Metadata-Only Poisoning
cs.CR
Submitted: 2026-10-10
Updated: 2026-10-10
Terminology
Sources
- Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark
- SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
- GLM-5: from Vibe Coding to Agentic Engineering
- From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills
- SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
- Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub
- SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
- SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
- "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
- Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
- Involuntary In-Context Learning: Exploiting Few-Shot Pattern Completion to Bypass Safety Alignment in GPT-5.4
- Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
- Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
- Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distribution
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
- SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
- Skill Retrieval Augmentation for Agentic AI
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs