build1 publisher
A 328-case benchmark traces injected instructions across seven kinds of agent-harness state
HarnessSafe, from Beijing University of Posts and Telecommunications with China Telecom and the Beijing Academy of Artificial Intelligence, reports that containment depends on which carrier holds the attacker's text and on which model is driving the harness.
Publishers:arxiv.org
Reality
- Evidence44
- Adoption
- Insufficient
- Hype gap+15
- Incentives40
- Confidence55