forward

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation provides a link to official vendor software (Forward Networks Linux collector) at fwd.app for administrative workflows.
  • [PROMPT_INJECTION_INDIRECT]: The skill processes network analysis data, representing a surface for indirect prompt injection.
  • Ingestion points: Network snapshots, device configurations, and NQE query results (SKILL.md).
  • Boundary markers: The instructions provide guidance on distinguishing between ad-hoc results and official Forward Library results.
  • Capability inventory: The skill can update network devices, create/modify network settings, and initiate data collection tasks.
  • Sanitization: All data operations are handled through the structured Forward Networks API and the mcp-server binary.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — forward