get-token-metadata

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured interface for the 'artblocks-mcp' tool to retrieve metadata from the Art Blocks platform. No malicious instructions, obfuscation, or unauthorized access patterns were identified.\n- [PROMPT_INJECTION]: The skill acts as an ingestion point for external blockchain metadata which constitutes a surface for Indirect Prompt Injection.\n
  • Ingestion points: The project.description and token.features fields returned by the get_token_metadata tool.\n
  • Boundary markers: No explicit instruction to treat external metadata as untrusted is present in the skill documentation.\n
  • Capability inventory: The skill is limited to data retrieval and does not have access to sensitive file systems, environment variables, or administrative commands.\n
  • Sanitization: No sanitization or filtering logic is defined for the retrieved text strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 05:26 PM