# SkillTester: Benchmarking Utility and Security of Agent Skills

arXiv: https://arxiv.org/abs/2603.28815 · HTML: https://mlsanity.com/paper/2603.28815/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 13 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Built on by (most cited first, 10 of 10)

- [SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills](https://mlsanity.com/paper/2604.06550/) (2026)
- [MMSkills: Towards Multimodal Skills for General Visual Agents](https://mlsanity.com/paper/2605.13527/) (2026)
- [Counterfactual Trace Auditing of LLM Agent Skills](https://mlsanity.com/paper/2605.11946/) (2026)
- [Co-Evolving Skill Generation and Policy Optimization](https://mlsanity.com/paper/2606.08755/) (2026)
- [Harness Engineering as Categorical Architecture](https://mlsanity.com/paper/2605.12239/) (2026)
- [Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills](https://mlsanity.com/paper/2608.20614/) (2026)
- [SkillFab: An Agent-Native Skill Production Platform](https://mlsanity.com/paper/2607.03780/) (2026)
- [Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation](https://mlsanity.com/paper/2608.08146/) (2026)
- [Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems](https://mlsanity.com/paper/2609.30383/) (2026)
- [When Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use](https://mlsanity.com/paper/2609.32274/) (2026)

## Abstract (arXiv)

This technical report presents SkillTester, a tool for evaluating the utility and security of agent skills. Its evaluation framework combines paired baseline and with-skill execution conditions with a separate security probe suite. Grounded in a comparative utility principle and a user-facing simplicity principle, the framework normalizes raw execution artifacts into a utility score, a security score, and a three-level security status label. More broadly, it can be understood as a comparative quality-assurance harness for agent skills in an agent-first world. The public service is deployed at https://skilltester.ai, and the broader project is maintained at https://github.com/skilltester-ai/skilltester.