use-ts-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates templates and routing logic that interact with untrusted data from the blockchain.
- Ingestion points: The skill facilitates processing external data via blockchain view functions and resource queries (e.g., in
view-functions/andhooks/directories). - Boundary markers: No explicit delimiters or safety warnings for handling potentially malicious blockchain state are included in the generated patterns.
- Capability inventory: The generated code includes capabilities for network communication with blockchain nodes and transaction submission via
aptos.signAndSubmitTransaction. - Sanitization: The provided code patterns do not include explicit sanitization or validation logic for data retrieved from on-chain sources.
Audit Metadata