drawio-logical-diagrams

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions or prompt injection patterns were found. The skill follows established patterns for generating structured XML data.
  • [SAFE]: The skill does not access sensitive local files, credentials, or environment variables. Access is limited to standard diagram generation tasks.
  • [SAFE]: There are no external network operations, downloads from untrusted sources, or remote code execution patterns.
  • [SAFE]: Indirect Prompt Injection Surface Analysis:
  • Ingestion points: The skill processes user-supplied system or process descriptions to generate diagrams (SKILL.md).
  • Boundary markers: Not explicitly defined for the input content, but the output is strictly constrained to XML format.
  • Capability inventory: Includes 'Write' access to save .drawio files and 'Bash' for potential local validation (SKILL.md).
  • Sanitization: The instructions mandate escaping special characters for XML validity, which provides basic structural sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:53 PM