Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution

About

Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding sockets. This design fails against prompt injection, tool misuse, and model-controlled exfiltration because the agent can both use and reveal the same bearer credential. We present CapSeal, a capability-sealed secret mediation architecture that replaces direct secret access with constrained invocations through a local trusted broker. CapSeal combines capability issuance, schema-constrained HTTP execution, broker-executed SSH actions, anti-replay session binding, policy evaluation, and tamper-evident audit trails. We describe a Rust prototype integrated with an MCP-facing adapter, formulate conditional security goals for non-disclosure, constrained use, replay resistance, and auditability, and define an evaluation plan spanning prompt injection, tool misuse, and SSH abuse. The resulting system reframes secret handling for agentic systems from handing the model a key to granting the model a narrowly scoped, non-exportable action capability.

Shutong Jin, Ruiyi Guo, Ray C. C. Cheung• 2026

Related benchmarks

TaskDatasetResultRank
Key Leakage PreventionHTTP real_e2e
Leakage Rate0.00e+0
3
Key Leakage PreventionSSH real_e2e
Leakage Rate0.00e+0
3
Request CompletionHTTP Benign Requests
Completion Rate100
3
Request CompletionSSH Benign Requests
Completion Rate100
3
Unauthorized Credential Use MitigationHTTP real_e2e (test)
Unauthorized Rate0.00e+0
3
Unauthorized Credential Use MitigationSSH real_e2e (test)
Unauthorized Rate0.00e+0
3
Showing 6 of 6 rows

Other info

Follow for update