nexus-sdk-swap-flows
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions to bypass safety filters or override agent instructions were detected.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations are present.
- [Unverifiable Dependencies] (SAFE): The skill does not perform any package installations or remote script executions.
- [Obfuscation] (SAFE): The content is clear-text markdown with no hidden characters, encoding, or homoglyphs.
- [Indirect Prompt Injection] (SAFE): While the skill defines interfaces for processing transaction data, it does not ingest untrusted natural language data that could lead to indirect injection.
- Ingestion points: SDK method parameters in
SKILL.md. - Boundary markers: N/A (Structured data types like Hex and bigint used).
- Capability inventory: Blockchain transaction execution via
sdk.swapAndExecute. - Sanitization: Implicitly handled by SDK types.
Audit Metadata