🛰️ Daily AI Frontier
‹ back to 2026-07-22

OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills

Research LLM Agents

Merged summary

TL;DR - OpenSkillRisk is a safety benchmark built from 263 risky third-party skills found in public marketplaces. Tests show that current CLI agents and LLMs cannot reliably prevent unsafe execution, with even the safest configurations acting unsafely in roughly 17% of cases.

  • Evaluates three mainstream CLI agent frameworks and 13 state-of-the-art LLMs in controlled sandboxes.
  • Covers seven threat categories paired with standardized user tasks.
  • Context-dependent and system-level risks were especially difficult for agents to avoid.
  • Common failures include missing risks, recognizing them too late, and exceeding the user’s intended scope.

Sources (1)

OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills

arXiv cs.CL Qiyuan Liu, Tingfeng Hui, Kun Zhan, Kaike Zhang, Ning Miao 2026-07-22 arXiv:2607.20121

TL;DR - OpenSkillRisk is a safety benchmark built from 263 risky third-party skills found in public marketplaces. Tests show that current CLI agents and LLMs cannot reliably prevent unsafe execution, with even the safest configurations acting unsafely in roughly 17% of cases.

  • Evaluates three mainstream CLI agent frameworks and 13 state-of-the-art LLMs in controlled sandboxes.
  • Covers seven threat categories paired with standardized user tasks.
  • Context-dependent and system-level risks were especially difficult for agents to avoid.
  • Common failures include missing risks, recognizing them too late, and exceeding the user’s intended scope.
item →