igrantio-credential-schema-loyalty-card
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ask the user a series of questions regarding environment, API keys, and credential formats, and to wait for answers before proceeding to generate code. This interaction creates an attack surface for indirect prompt injection.
- Ingestion points: User-supplied answers to the eight configuration questions in the "Ask the integrator first" section.
- Boundary markers: Absent. The instructions do not define delimiters or explicit warnings to the agent to treat this user input strictly as data.
- Capability inventory: The skill provides instructions for the agent to construct and potentially execute API calls to the iGrant.io OpenID4VC API (
POST /v2/config/digital-wallet/openid/sdjwt/credential-definition). - Sanitization: No sanitization, validation, or escaping requirements are specified for the data collected from the user.
- [EXTERNAL_DOWNLOADS]: The skill references external resources for schema templates and documentation.
- Evidence: The documentation points to the iGrant.io verifiable data registry on GitHub (
github.com/decentralised-dataexchange/verifiable-data-registry) and official documentation (docs.igrant.io). These references provide the source of truth for the schemas.
Audit Metadata