balise-affinity-mcp

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides JavaScript patterns for use with an execute_script capability. These scripts automate tasks such as creating shapes, formatting text, and managing document layers within the Affinity application. The logic is self-contained and uses internal module paths (e.g., /document, /nodes).
  • [DATA_EXFILTRATION]: Document inspection routines retrieve metadata including document titles, file paths, and session UUIDs. This data is used solely for session management and visual verification via the render_selection and render_spread tools, with no indicators of unauthorized external transmission.
  • [PROMPT_INJECTION]: No malicious instruction overrides or safety bypass attempts were found. The skill emphasizes small, reversible edits and explicit user consent for destructive actions like flattening or deleting broad selections.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 01:13 AM