ENTITY
SANDBOXESCAPEBENCH
SANDBOXESCAPEBENCH
PulseAugur coverage of SANDBOXESCAPEBENCH — every cluster mentioning SANDBOXESCAPEBENCH across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
1 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
LLM Agent Security: Tool Schema Exploits Outpace Container Escapes
A recent analysis highlights two distinct security vulnerabilities in LLM agent deployments: container escapes and tool schema layer exploits. While container hardening addresses the former, the latter, which involves t…
-
New benchmark quantifies LLM sandbox escape capabilities
Researchers have developed SANDBOXESCAPEBENCH, a new benchmark designed to safely evaluate the ability of large language models (LLMs) to break out of containerized sandbox environments. The benchmark, implemented as a …