Skills
skills/nitemaeric/dragonruby-skills/dragonruby/Gen Agent Trust Hub

dragonruby

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external data through file reads and network requests, creating a surface for indirect prompt injection. * Ingestion points: args.gtk.read_file, args.gtk.http_get, and args.gtk.parse_json_file in SKILL.md. * Boundary markers: None identified in the provided documentation. * Capability inventory: File system writes via args.gtk.write_file, text rendering to labels, and development console interaction via GTK.console.set_command. * Sanitization: No explicit sanitization or validation of external data is demonstrated in the examples.
  • [EXTERNAL_DOWNLOADS]: The skill documents the use of args.gtk.http_get to retrieve remote resources from external URLs, which is a standard feature for the documented engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 07:03 PM