Agents are manipulated into using file, database, API, and cloud-management tools to enumerate and extract credentials from configuration files, environment variables, process memory, databases, key vaults, and instance metadata, and to correlate fragments into full credentials.
Credential harvesting via agent tools and storage
CCC.MARefArc.TH32
Related Capabilities
| ID | Title | Description |
|---|---|---|
| CCC.MARefArc.CP08 | Built-in trusted tools | A collection of bundled, trusted tools providing fundamental capabilities: the MCP client bridge to the external MCP layer, a sandboxed shell, workspace I/O, and web search. |
| CCC.MARefArc.CP10 | Sandboxed workspace file system | A sandboxed, persistent file system that agents use to read and write files, enabling work with large artifacts. |
| CCC.MARefArc.CP07 | Unified sandboxed agent runtime | Secure, sandboxed environment where all agentic reasoning and execution occurs, providing task state management for pause/resume/handoff and intercepting and validating tool calls with credentials handled securely within the sandbox. |
| CCC.MARefArc.CP12 | Authoritative knowledge source bases | Internal and external repositories of structured data, unstructured documents, and graph-based representations that provide authoritative information for grounding. |
Related Controls
| ID | Title | Description |
|---|---|---|
| CCC.MARefArc.CN15 | Agentic System Credential Protection Framework | Prevent agents from discovering, extracting, or misusing credentials by brokering secrets outside agent-accessible surfaces and constraining tool access to credential stores. |