igrantio-api-team-management
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes official domains belonging to the provider (igrant.io) for all API endpoints and documentation references, which is consistent with its stated purpose.
- [SAFE]: Credential management instructions follow industry best practices by advising that OWS API keys be stored securely on the server in environment variables or secret managers, ensuring they are not exposed in the client-side environment.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to fetch and follow external vendor documentation as the definitive source of truth, creating a potential data ingestion surface.
- Ingestion points: Documentation pages and the OpenAPI specification file (oid4vc.yaml) hosted at docs.igrant.io.
- Boundary markers: None present; the instructions explicitly state that the external documentation takes precedence over the skill text.
- Capability inventory: The agent can perform administrative operations including creating, updating, and deleting organization admins via the iGrant.io API.
- Sanitization: No specific sanitization or validation of the fetched documentation content is described.
- Note: This surface is assessed as safe as it targets the official resources of the trusted service provider.
Audit Metadata