crypto-research-desk
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill instructions define a purely organizational and synthesis task for crypto market data. No executable code or shell commands are present. The skill only defines formatting and merging logic for data.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external 'data seat' content into a consolidated report. This creates an ingestion surface for untrusted data. Ingestion points: The skill processes 'raw gather-seat data'. Boundary markers: None explicitly defined to separate input data from instructions. Capability inventory: The skill instructions do not utilize any tools, subprocesses, file operations, or network calls. Sanitization: No explicit data validation or cleaning instructions are provided. The potential for impact is extremely limited given the lack of system-level capabilities.
Audit Metadata