gateway
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions as a proxy that forwards user input to various child MCP servers through the
invokecommand. This creates an attack surface where malicious or unexpected input could be passed to downstream tools. - Ingestion points: Arguments passed to the
invoke {name, arguments}command. - Boundary markers: None defined in the skill documentation to separate untrusted data from instructions.
- Capability inventory: The skill is designed to spawn child processes (MCP servers) and execute their tools.
- Sanitization: There is no evidence of input validation or sanitization before arguments are passed to the target servers.
- [COMMAND_EXECUTION]: The setup instructions involve manual compilation of source code using
go buildand running the resulting binary. While standard for developer-oriented tools, this involves the execution of locally built code that manages other processes.
Audit Metadata