telemetry-ops

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation and configuration examples. No executable code, hidden scripts, or malicious persistence mechanisms were found.- [CREDENTIALS_UNSAFE]: The Cisco Catalyst configuration examples use 'public' as a sample SNMP community string. While this is an insecure default, it is presented as a documentation placeholder rather than an embedded operational secret.- [PROMPT_INJECTION]: The skill processes untrusted network telemetry data, which constitutes a surface for indirect prompt injection.
  • Ingestion points: syslog-mcp, snmptrap-mcp, ipfix-mcp, and gnmi-mcp.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: Querying syslog counts, linkDown events, flow anomalies, and gNMI device state.
  • Sanitization: No sanitization logic is described in this documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — telemetry-ops