nsm-ids-triage

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly read-only and operates on existing packet capture files on disk. It does not support live sniffing or network writes, minimizing the attack surface.
  • [COMMAND_EXECUTION]: The skill utilizes a set of well-defined tools (nsm_status, nsm_update_rules, nsm_alerts, nsm_analyze) through a specific MCP server (nsm-mcp). These tools are purpose-built for network security monitoring and do not provide arbitrary shell access.
  • [DATA_EXFILTRATION]: No data exfiltration patterns were identified. The skill focuses on local analysis, and its interactions are confined to the defined MCP toolset.
  • [PROMPT_INJECTION]: The instructions provide robust guidance to the agent on how to interpret IDS alerts honestly, specifically preventing the agent from misinterpreting a lack of signatures as a 'clean' network traffic verdict.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:47 AM
Security Audit — agent-trust-hub — nsm-ids-triage