Research
Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills
Publication date unknown · Discovered arxiv.org
Page published
Publication date unknown · First observed: 20 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Agent-skill permission declarations can obscure shell, filesystem, network, and credential access, making capability-based inspection important before granting skills authority within an agent session.
“Beyond Maliciousness” studies 6,309 agent-skill marketplace listings using static analysis, dependency provenance checks, and instrumented sandbox execution. Seven in ten listings carry evidence of at least one elevated capability, while 59% of listings declaring permissions understate their bundles’ capabilities. The study finds that permission declarations remove confirmation prompts rather than restrict access.