ssh-ops
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of administrative shell commands both locally and on remote hosts via SSH, including tools like ssh, scp, and docker-compose.\n- [EXTERNAL_DOWNLOADS]: The configuration for the ssh-mcp server uses
npx -y, which downloads and executes thessh-mcppackage from the public npm registry without user intervention.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to capture and report output from remote commands, which creates an attack surface for indirect prompt injection if the remote system is compromised.\n - Ingestion points: Remote command outputs in references/remote-ops.md and references/ssh-mcp.md.\n
- Boundary markers: Absent.\n
- Capability inventory: Remote command execution, file system access, and file transfer via scp.\n
- Sanitization: Absent.
Audit Metadata