AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
- Published
- Record updated
Summary
AgentCap is a runtime authorization layer that takes the authorization decision out of the language model and mediates each tool invocation through an MCP wrapper. It checks declared intents against policy constraints, then issues short-lived, budget-bounded capability tokens validated at the tool boundary. Across AgentDojo and InjecAgent it reduced attack success in every evaluated setting, reaching 0% with GPT-5.4 on both benchmarks and blocking all attempted unauthorized executions in controlled adversarial scenarios.
Mitigation
AgentCap itself is the mitigation: a runtime authorization layer that mediates every tool invocation through an MCP wrapper, validating short-lived, budget-bounded capability tokens at the tool boundary, with delegation limited to session-bound parent-child chains.
Related items
- InfoChatGPT will now make you animated GIFsSame vendor · The Verge (AI)
- MediumResearchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak ToolkitSame vendor · The Hacker News
- InfoForrester gave Endor Labs the highest score possible in seven criteria, including innovation, AI application flaws, AI SCA, and AI coding toolchain. | Endor LabsSame vendor · Endor Labs Blog
- InfoUber only fulfilled 4 rides from AI agents last quarterSame vendor · The Verge (AI)
- InfoSam Altman addresses RAM comments: People should ‘put as much as they want in their computers’Same vendor · The Verge (AI)