offchain-ens-subname-sdk
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
@thenamespace/offchain-managernpm package to provide its core subname management features. - [INDIRECT_PROMPT_INJECTION]: The skill fetches external data such as text records and metadata from the Namespace API, which represents a potential surface for indirect prompt injection.
- Ingestion points: Data enters the context via
getFilteredSubnames,getSingleSubname, andgetTextRecordsmethods inSKILL.md. - Boundary markers: No explicit boundary markers or safety instructions for handling embedded data are present in the examples.
- Capability inventory: The skill is designed for specific API-based management tasks and does not have access to dangerous capabilities like arbitrary command execution, file system manipulation, or dynamic script evaluation.
- Sanitization: No explicit sanitization or validation of the retrieved API data is demonstrated in the documentation.
Audit Metadata