radkit-remote-access
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external implementation repository at
https://github.com/CiscoDevNet/radkit-mcp-server-community. This repository is provided by a well-known technology vendor and is used to deliver the core functionality of the skill. - [COMMAND_EXECUTION]: The skill defines tools such as
exec_cli_commands_in_deviceandexec_commandfor remote device interaction. These capabilities are central to the skill's functionality and include parameters for timeouts and output truncation to maintain control over execution. - [PROMPT_INJECTION]: The skill defines an interface for ingesting data from remote network devices (CLI output and SNMP attributes), which represents a vulnerability surface for indirect prompt injection. Ingestion points:
exec_cli_commands_in_deviceandget_device_attributes. Boundary markers: Output truncation is available viamax_lines, though explicit instruction-isolation markers are not specified. Capability inventory: Remote CLI and SNMP execution. Sanitization: No explicit sanitization of device-returned content is mentioned. This surface is characteristic of network management tools and no malicious patterns were identified.
Audit Metadata