pith. machine review for the scientific record. sign in

Taming Various Privilege Escalation in

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

FORTIS: Benchmarking Over-Privilege in Agent Skills

cs.AI · 2026-05-09 · unverdicted · novelty 7.0 · 2 refs

FORTIS benchmark shows over-privilege is the norm in LLM agent skill selection and execution, with models reaching for higher-privilege skills and tools than required across ten frontier models and three domains.

citing papers explorer

Showing 1 of 1 citing paper.

  • FORTIS: Benchmarking Over-Privilege in Agent Skills cs.AI · 2026-05-09 · unverdicted · none · ref 14 · 2 links

    FORTIS benchmark shows over-privilege is the norm in LLM agent skill selection and execution, with models reaching for higher-privilege skills and tools than required across ten frontier models and three domains.