RuntimeTickets: Source-Grounded Security Obligations for Agent Skills
cs.CR, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/cisco-ai-defense/skill-scanner
Terminology
Sources
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
- Securing AI Agents with Information-Flow Control
- Defeating Prompt Injections by Design
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- HazardAuditor: From Executable Threats to Safer Computer-Use Agents
- MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
- Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem
- Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
- Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
- SkillGuard: A Permission-Centric Framework for Agent Skill Security
- AIRGuard: Guarding Agent Actions with Runtime Authority Control
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
- Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
- Progent: Securing AI Agents with Privilege Control
- Scan the Skill, Govern the Action: Composing Registry Verdicts with Runtime Consequence Control
- AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents
- CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data