fusion-help-api

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference for the Fusion Help REST API, covering discovery, authentication, and CRUD operations for help articles, FAQs, and release notes.
  • [SAFE]: All network operations and base URLs target official vendor domains (fusion.equinor.com, fusion-dev.net) or well-known services (Azure AD, Discovery service).
  • [SAFE]: Integration patterns provided for React, C#, and Python use standard, reputable libraries (e.g., azure-identity, requests) and follow best practices by utilizing DefaultAzureCredential rather than hardcoded secrets.
  • [SAFE]: The skill includes clear security and authorization guidance, noting that administrative actions require specific roles and providing the necessary Azure AD resource identifiers for different environments.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data from the Help API which constitutes a potential surface for indirect prompt injection.
  • Ingestion points: REST API responses from /articles, /faqs, and /release-notes (documented in references/api-endpoints.md).
  • Boundary markers: Absent; the instructions do not specify the use of delimiters when the agent processes help content.
  • Capability inventory: The skill allows the agent to generate code for network operations (REST calls) and provide information on managing help content.
  • Sanitization: Server-side validation rules are documented for write operations, though no client-side sanitization of retrieved markdown content is explicitly required in the integration patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 08:19 AM