CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection
cs.CR, cs.AI
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: 16 pages, 2 figures, 8 tables, including appendices
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines
- Formal Analysis and Supply Chain Security for Agentic AI Skills
- Dynamic Malicious Skills in Agentic AI
- How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
- Detecting Malicious Agent Skills in the Wild using Attention
- SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
- MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
- SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
- One Skill, Two Masters: Serving Users and Attackers through Skill Injection
- Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem
- SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
- Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
- SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- Kimi K2.5: Visual Agentic Intelligence
- STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
- Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
- Exploiting LLM Agent Supply Chains via Payload-less Skills
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
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills