drawio-logical-diagrams

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were detected in the skill files. The instructions are strictly focused on the generation of draw.io XML diagrams.\n- [SAFE]: The skill relies on local reference documents for templates and styles, avoiding any external downloads or remote code execution risks.\n- [SAFE]: Assessment of indirect prompt injection surfaces:\n
  • Ingestion points: User requests describing systems (SKILL.md)\n
  • Boundary markers: No explicit markers for input data\n
  • Capability inventory: Bash, Read, Write (scoped to file creation)\n
  • Sanitization: Instructions specify escaping special characters in XML output
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 09:43 AM