skills/plurigrid/asi/z/Gen Agent Trust Hub

z

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill exposes an aptos_intent tool that interprets natural language to perform blockchain operations. This creates a surface where untrusted data could potentially influence financial transactions.
  • Ingestion points: mcp__world_z_aptos__aptos_intent tool input.
  • Boundary markers: None defined in the skill configuration.
  • Capability inventory: Includes high-impact financial operations such as aptos_transfer, aptos_swap, and aptos_stake.
  • Sanitization: No explicit sanitization or instruction-ignoring delimiters are specified in this skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:50 PM