nft-engineer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE] (SAFE): No malicious instructions, obfuscation, or data exfiltration logic were detected in the provided skill files.
- [PROMPT_INJECTION] (LOW): The skill processes untrusted smart contract and metadata files, creating an ingestion surface for embedded instructions. 1. Ingestion points: .sol and .json files matching glob patterns in references/validations.md. 2. Boundary markers: Absent. 3. Capability inventory: The agent provides technical advice and code generation; no network access or subprocess execution capabilities were identified. 4. Sanitization: Absent.
Audit Metadata