diagrams-js/diagrams-js-plugin-system

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a framework for importing external data formats (e.g., Docker Compose, YAML, SVG), which establishes an ingestion surface for potentially untrusted data that could contain malicious instructions.
  • Ingestion points: Custom importers such as the docker-compose importer defined in SKILL.md process external file content.
  • Boundary markers: The provided examples do not include boundary markers or specific instructions for the agent to ignore embedded commands within processed data.
  • Capability inventory: The plugin system supports creating nodes, attaching metadata, and exporting diagrams to various formats, which could be leveraged if an injection is successful.
  • Sanitization: The documentation does not demonstrate sanitization or validation of the imported content, which is standard for architectural documentation but represents a potential risk surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 01:02 AM
Security Audit — agent-trust-hub — diagrams-js/diagrams-js-plugin-system