routeros-diagnostics-monitoring
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and analyze potentially untrusted data from network devices.
- Ingestion points: Untrusted data enters the agent context through the output of
/log/print(which displays system events, including user-supplied usernames or DHCP hostnames) and/tool/sniffer(which captures raw network traffic). - Boundary markers: The instructions do not specify any delimiters or special markers to wrap log content or packet data to distinguish it from system instructions.
- Capability inventory: The skill enables the agent to execute various CLI commands on a RouterOS device, including configuration changes and diagnostic tools.
- Sanitization: There is no requirement for the agent to sanitize or escape log messages or packet payloads, which could theoretically contain prompt injection payloads designed to trick the agent while it is troubleshooting a network issue.
Audit Metadata