radkit-remote-access
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides tools like exec_cli_commands_in_device and exec_command to execute CLI commands on remote network devices. This behavior is the stated primary purpose of the skill.
- [EXTERNAL_DOWNLOADS]: The skill references the official CiscoDevNet/radkit-mcp-server-community repository for its server implementation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from remote network devices, creating a surface for potential indirect prompt injection. 1. Ingestion points: CLI output and SNMP polling results from remote devices. 2. Boundary markers: Instructions suggest using max_lines for truncation but do not specify prompt-level delimiters to protect against embedded instructions. 3. Capability inventory: The skill allows the agent to execute CLI commands and potentially modify configurations on network infrastructure. 4. Sanitization: The documentation does not specify any sanitization or filtering of device output before it is passed to the agent.
Audit Metadata