mantle-smart-contract-developer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a purely instructional framework for gathering requirements and providing architectural guidance. No network operations, file system modifications, or sensitive data access patterns were identified in the instructions or reference files.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface as it processes untrusted user requirements to generate a development brief. However, the risk is negligible due to the absence of executable capabilities.
- Ingestion points: User-provided contract purpose, user flows, and environment details are captured in
SKILL.md. - Boundary markers: No explicit delimiters or boundary instructions for user-supplied data are present.
- Capability inventory: The skill contains no tools or scripts and lacks capabilities for subprocess execution, network requests, or file writes.
- Sanitization: No validation or sanitization of user input is performed before interpolation into the output brief.
Audit Metadata