soia-dev-drawio-visio-diagrams

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/drawio_cli.py executes the local drawio Desktop binary via subprocess.run to perform file conversions and exports. The implementation follows security best practices by passing arguments as a list rather than a shell string, effectively mitigating shell injection risks.
  • [SAFE]: The skill demonstrates high security awareness in its file handling logic. Specifically, scripts/inspect_vsdx.py includes explicit checks to prevent ZIP path traversal (verifying member names) and enforces strict limits on uncompressed data sizes and XML complexity to protect against resource exhaustion (ZIP bombs).
  • [PROMPT_INJECTION]: The skill extracts shape text and labels from external diagrams using inspect_vsdx.py and inspect_drawio.py. This data is presented to the agent in the prompt context. While this creates a surface for indirect prompt injection, the skill mitigates this by cleaning extracted text (removing HTML/extra whitespace) and placing the content within clear markdown boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 03:33 AM
Security Audit — agent-trust-hub — soia-dev-drawio-visio-diagrams