InfoResearchPreprintLLM-specific
Guarding the Kingdom of Skill-Based Agents in the AI Dynasty of Computation: Control-Flow Integrity for Agent Skills
- Published
- Record updated
Summary
SkillCFI carries control-flow integrity over to skill-based LLM agents. Its compiler derives agent instructions and an executable contract from one skill, and a deterministic runtime enforcer admits tool requests only on trusted evidence. On eight self-written skills across 770 sessions, it blocked all 240 violations that a permission allowlist admitted, though no public skills were accepted as written.
Related items
- HighGHSA-3mgh-93r5-r7jf: CodeWhale: exec_shell parallel-readonly classifier auto-approves fd/rg/git grep exec flags enabling silent RCESimilar attack · GitHub Advisory Database
- HighGHSA-8hp3-xxrg-v9c8: CodeWhale: Automation auto_approve defaults to true, bypassing the task-path hardening fix for silent recurring agent executionSimilar attack · GitHub Advisory Database
- MediumCVE-2026-18883: ServiceNow Email Response AI Agent indirect prompt injection flawSimilar attack · NVD/CVE Database
- InfoAI-Defined Vehicles: Securing the Decisions That Drive Vehicle BehaviorSimilar attack · VicOne Blog
- HighCVE-2026-75612: yt-mcp arbitrary file read through add_attachment file_pathSimilar attack · NVD/CVE Database