whale-index

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface.
  • Ingestion points: The skill fetches trader data and statistics from the Hyperliquid Discovery leaderboard using discovery_top_traders and discovery_get_trader_state within SKILL.md and references/daily-monitoring.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the templates that process external trader information.
  • Capability inventory: The skill possesses the ability to manage financial assets using tools such as strategy_create_mirror, strategy_top_up, and strategy_close_strategy.
  • Sanitization: The skill does not perform validation or sanitization on external string data (like trader names or metadata) before utilizing it in its decision-making logic.
  • [NO_CODE]: The skill consists entirely of markdown-based instructions and logic for the agent to follow and does not include any executable scripts, binaries, or compiled code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 11:59 PM