The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from external sources, which represents a potential attack surface for indirect prompt injection.
Ingestion points: Several API operations defined in SKILL.md involve external inputs, such as credentialDefinitionUri for schema previews and transactionData for validation.
Boundary markers: The instructions lack explicit guidance for the agent to treat data from these external sources as untrusted or to use specific delimiters to prevent instruction leakage.
Capability inventory: The skill enables the agent to perform network requests and state modifications through the iGrant.io API.
Sanitization: There is no mention of sanitization, filtering, or validation steps for external content within the skill's instructions.

igrantio-api-issuer