igrantio-dcapi-ios
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill outlines a process for ingesting and verifying external digital credentials, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The skill processes external presentation responses (
vpTokenResponse) and mdoc doctypes as described in the Workflow section ofSKILL.md. - Boundary markers: There are no specific instructions or delimiters provided to ensure the agent ignores or isolates potential instructions embedded within the credential data fields.
- Capability inventory: The workflow includes posting processed data to a backend proxy and performing verification checks across multiple scripts.
- Sanitization: While the skill details decoding and verifying the trust status of the token, it lacks explicit guidance on sanitizing or validating the credential content to prevent malicious payloads from influencing agent behavior.
Audit Metadata