EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents
EvoSafeHarness auto-synthesizes per-model, per-domain safety harnesses, cutting prompt-injection attack success on AgentDojo to 0.0% at 82.8% utility.
48
Product
DecodingTrust-Agent
- Mentions · 7d0
- Mentions · 30d0
- All mentions1
- First seenSep 4, 2026
- Last mentionedSep 4, 2026
Timeline
1 articles · newest firstAppears with
- CaMeLproduct · 1
- Agent-SafetyBenchproduct · 1
- EvoSafeHarnessproduct · 1
- AgentDojoproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.