igrantio-credential-schema-mobile-driving-license
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch schema templates and metadata from external URLs hosted on GitHub.
- Evidence:
- Fetches templates from:
https://github.com/decentralised-dataexchange/verifiable-data-registry - Retrieves raw JSON schemas from:
https://raw.githubusercontent.com/decentralised-dataexchange/verifiable-data-registry/main/credentialSchemas/claimPathPointer/mobileDrivingLicense/2026.4.1/mso_mdoc.schema.json - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface where instructions or data retrieved from the external GitHub registry could influence the agent's behavior during API request construction.
- Ingestion points: The agent is instructed to fetch and process JSON schema and metadata files from the
decentralised-dataexchangerepository on GitHub. - Boundary markers: None present; the skill instructs the agent to rely on the registry content if it disagrees with the local documentation.
- Capability inventory: The skill involves constructing and performing
POSTrequests to the iGrant.io OpenID4VC API (/v2/config/digital-wallet/openid/sdjwt/credential-definition). - Sanitization: No specific sanitization or validation of the fetched JSON structure is mentioned before interpolation into API payloads.
Audit Metadata