Jobs / Security
Can agents do security work?
Find, exploit, and fix vulnerabilities; monitor and defend systems.
- US jobs
- 190,650 (0.1% of employment)
- Typical wage
- $129K a year (employment-weighted mean of occupation medians)
- Occupations
- 4 in O*NET 31.0
- Evidence
- 5 benchmarks from 5 institutions
Task level
Partial
Mixed. Capture-the-flag and vulnerability-reproduction tasks are near their ceiling: Anthropic reports 100% on its 35-task Cybench subset, and the top CyberGym entry reproduces 98.5% of vulnerabilities (Level 1). Exploitation of real web applications is not shown: the last published CVE-Bench result is 12.5% (GPT-4o, 2025), and we found no newer frontier result.
Evidence: Cybench, CyberGym, CVE-Bench — by Stanford University, UC Berkeley, and UIUC. Reading dated 23 Sep 2026.
Agents succeed on some scoped tasks. Reliable or end-to-end work is not shown.
Project level
Unexplored
No benchmark in our collection tests security work at project scale, such as a full penetration test, a security review of a whole system, or a compliance audit.
No benchmark covers this work yet.
Benchmarks for this work
Also relevant
These benchmarks cover part of this family's work.
Functions: Vulnerability researchIncident responseCompliance operationsFinOpsLong-horizon autonomy
What we do not know
- Benchmarks measure tasks, not whole jobs. A job is a bundle of tasks, judgment, and relationships.
- Capability is not adoption. A task that agents can do in a benchmark may still be done by people at work.
- Most results come from single runs. Reliability over many runs is often unknown.
Occupations in this family
Sorted by US employment (BLS OEWS May 2025). O*NET sub-occupations share the employment figure of their SOC group.
| Occupation | SOC | US jobs |
|---|---|---|
| Digital Forensics Analysts | 15-1299.06 | (435K group) |
| Information Security Engineers | 15-1299.05 | (435K group) |
| Penetration Testers | 15-1299.04 | (435K group) |
| Information Security Analysts | 15-1212.00 | 191K |
How to cite
Credit the original work first: the benchmarks listed on this page, and their institutions.
Then, if you used this page:
Can Agents Work. "Can agents do security work?." https://canagentswork.com/jobs/security/ (accessed 2026-09-24). CC BY 4.0.@misc{caw-jobs-security,
title = {{Can agents do security work?}},
author = {{Can Agents Work}},
year = {2026},
howpublished = {\url{https://canagentswork.com/jobs/security/}},
note = {Accessed 2026-09-24. CC BY 4.0}
}