# Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware

arXiv: https://arxiv.org/abs/2607.02357 · HTML: https://mlsanity.com/paper/2607.02357/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 65 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 30 of 33)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024)
- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems](https://mlsanity.com/paper/2403.04960/) (2024)
- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024)
- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale](https://mlsanity.com/paper/2601.10338/) (2026)
- [Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks](https://mlsanity.com/paper/2602.20156/) (2026)
- [Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality](https://mlsanity.com/paper/2602.08004/) (2026)
- [RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage](https://mlsanity.com/paper/2502.08966/) (2025)
- [Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning](https://mlsanity.com/paper/1801.08917/) (2018)
- [Backstabber's Knife Collection: A Review of Open Source Software Supply Chain Attacks](https://mlsanity.com/paper/2005.09535/) (2020)
- [Contextual Agent Security: A Policy for Every Purpose](https://mlsanity.com/paper/2501.17070/) (2025)
- [Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework](https://mlsanity.com/paper/2601.11893/) (2026)
- ["Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild](https://mlsanity.com/paper/2602.06547/) (2026)
- [Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems](https://mlsanity.com/paper/2604.03081/) (2026)
- [Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems](https://mlsanity.com/paper/2504.11168/) (2025)
- [SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents](https://mlsanity.com/paper/2602.14211/) (2026)
- [SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills](https://mlsanity.com/paper/2604.06550/) (2026)
- [How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study](https://mlsanity.com/paper/2604.03070/) (2026)
- [MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills](https://mlsanity.com/paper/2606.07131/) (2026)
- [Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks](https://mlsanity.com/paper/2511.15203/) (2025)

## Built on by (most cited first, 10 of 10)

- [ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners](https://mlsanity.com/paper/2608.09732/) (2026)
- [MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection](https://mlsanity.com/paper/2608.19901/) (2026)
- [Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound](https://mlsanity.com/paper/2609.05920/) (2026)
- [Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting](https://mlsanity.com/paper/2607.07433/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)
- [SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness](https://mlsanity.com/paper/2609.06052/) (2026)
- [Runaway Reaction: When Benign Skills Compose into Malicious Behavior](https://mlsanity.com/paper/2610.05943/) (2026)
- [AgentSpy: Making AI Agent Behavior Observable](https://mlsanity.com/paper/2610.06001/) (2026)
- [Why Static Skill Inconsistencies Do Not Equate to Runtime Risks: A Behavioral Analysis of LLM Agent Execution](https://mlsanity.com/paper/2610.18927/) (2026)
- [CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection](https://mlsanity.com/paper/2610.20049/) (2026)

## Abstract (arXiv)

LLM coding agents increasingly rely on third-party agent skills from public marketplaces, which execute with the agent's privileges and create a software supply-chain attack surface: a malicious skill can steal credentials, exfiltrate source code, or install backdoors. Existing defenses use static skill scanners based on pattern matching or LLM-as-judge analysis, but it remains unclear whether they withstand adaptive evasions that preserve malicious behavior while changing payload appearance. This paper first presents an adversarial study of existing skill scanners through SkillCloak, a payload-preserving evasion framework that keeps the attack semantics intact while transforming their visible form. SkillCloak uses two complementary strategies: Structural Obfuscation, which rewrites visible payload indicators into semantically equivalent forms, and Self-Extracting Skill (SFS) Packing, which hides malicious components from the install-time view and restores them during agent execution. Across eight scanners and 1,613 in-the-wild malicious skills, SFS Packing bypasses every scanner at over 90%, while Structural Obfuscation bypasses over 80% on most static scanners and reaches 96% on a hybrid scanner, showing that appearance-based auditing is insufficient. Motivated by this finding, we propose SkillDetonate, a behavior-centric runtime auditor that executes skills in a sandbox and detects malicious effects through OS-boundary information-flow evidence rather than install-time appearance. SkillDetonate combines on-demand closure lift, which observes instructions materialized during execution, with marker-based taint analysis, which tracks sensitive-data flows across the agent context, files, processes, and network operations. The results show that SkillDetonate detects 97% of attacks at a 2% false-positive rate and sustains 87% detection on real-world malicious skills.