igrantio-credential-schema-software-statement
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and suggests fetching configuration documents from an external GitHub repository (
raw.githubusercontent.com/decentralised-dataexchange/verifiable-data-registry/...). These documents are used as the authoritative source for defining credential schemas in the iGrant.io API. - [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface where data fetched from an external registry is used to influence the agent's behavior and API configurations.
- Ingestion points: External JSON schema files retrieved from the
decentralised-dataexchangeGitHub organization, as described in the 'Source is the registry' section ofSKILL.md. - Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores any malicious instructions that might be embedded in the external schema data.
- Capability inventory: The skill facilitates the creation of credential definitions via the iGrant.io OWS API using
POSTrequests to/v2/config/digital-wallet/openid/sdjwt/credential-definition. - Sanitization: Absent. The skill does not mandate sanitization or validation of the fetched external content before it is used to populate API request payloads.
Audit Metadata