Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents

arXiv:2609.39065 · cs.CR, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/agent0ai/agent-zero

Project page: https://chenbihuan.github.io/paper/ccs18-chen-hawkeye.pdf

Terminology

Trace — 20× in this paper · explained in 2 episodes
Benchmark — 10× in this paper · explained in 2 episodes
Provenance — 9× in this paper · explained in 4 episodes
Verification — 7× in this paper · explained in 2 episodes
Benchmarking — 5× in this paper · explained in 3 episodes
Ablation — 3× in this paper · explained in 1 episode
Agent Skills — 3× in this paper · explained in 1 episode
Generative AI — 3× in this paper · explained in 2 episodes
Ablation study — 2× in this paper · explained in 1 episode
Agent Security Bench — 2× in this paper
Alignment — 2× in this paper · explained in 1 episode
Semantic Alignment — 2× in this paper · explained in 3 episodes
Analyzer — 1× in this paper · explained in 1 episode
Core — 1× in this paper · explained in 2 episodes
Model Context Protocol — 1× in this paper
Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes
Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
Progressive Disclosure — 1× in this paper · explained in 2 episodes
Pruning — 1× in this paper · explained in 4 episodes
Time to Exposure — 1× in this paper
WebAssembly (Wasm) — 1× in this paper · explained in 2 episodes

Sources

Related papers