extension-authorization

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a data ingestion surface through user profile creation and the collection of identity attributes (name, email) during the sign-in process. This data is stored in the backend and reflected in the frontend, creating a potential vector for indirect prompt injection if downstream systems or agents process these fields without proper isolation.
  • Ingestion points: The saveCallerUserProfile function in src/backend/mixins/Profile.mo and the attribute callback in src/backend/main.mo (processing sign-in data from MixinAuthorization).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are documented for the profile data or attribute fields.
  • Capability inventory: The skill manages role assignments (assignRole), authorization guards (hasPermission), and profile persistence.
  • Sanitization: The provided examples do not include explicit validation, filtering, or escaping of the user-supplied text before storage or retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 03:36 PM
Security Audit — agent-trust-hub — extension-authorization