routeros-app-yaml

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references JSON schemas for YAML validation and IDE integration hosted on the author's GitHub Pages (tikoci.github.io). These are vendor-provided resources used for documentation and configuration purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a configuration format and REST API for managing containerized applications on RouterOS. This creates a surface for indirect prompt injection if an agent uses these instructions to automate router configuration based on untrusted external data. * Ingestion points: YAML configuration files loaded via yaml-url or provided as inline content to the /app REST API endpoint (SKILL.md). * Boundary markers: None identified in the provided documentation or reference examples. * Capability inventory: Ability to create, manage, and execute containers, volumes, and networks on a RouterOS device via REST API calls (SKILL.md). * Sanitization: The skill does not specify sanitization or validation requirements beyond the YAML schema provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 07:02 AM