install-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses sensitive application configuration files, including
~/.claude.json,~/Library/Application Support/Claude/claude_desktop_config.json, and~/.cursor/mcp.json. These files are known to contain user-specific configuration and potentially session-related information. - [COMMAND_EXECUTION]: The instructions require the agent to perform file system operations, specifically reading and merging JSON content into local configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes existing configuration files, creating a potential surface for indirect prompt injection if those files contain untrusted content.
- Ingestion points: Local configuration files (
.claude.json,claude_desktop_config.json,mcp.json) for Claude and Cursor. - Boundary markers: The instructions do not define delimiters or warnings to ignore instructions that might be embedded in the existing configuration.
- Capability inventory: The agent has permissions to read and write to the local file system.
- Sanitization: No explicit sanitization or validation of the existing configuration data is performed before the merge operation.
Audit Metadata