Bankr Dev - Market Research

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): The skill creates a surface for indirect prompt injection by defining operations that ingest data from external, attacker-controlled sources (sentiment and social mentions). \n
  • Ingestion points: Operation templates such as 'What's the sentiment on {token}?' and 'Check social mentions for {token}' fetch data from the open web.\n
  • Boundary markers: The skill lacks delimiters or specific instructions to the agent to disregard embedded commands within the retrieved market data or sentiment strings.\n
  • Capability inventory: The skill is primarily focused on data retrieval and analysis (prices, charts, and market metrics).\n
  • Sanitization: No sanitization or filtering logic is specified for the external content before it is processed by the agent.\n- NO_CODE (SAFE): The provided file (SKILL.md) is purely informational, containing markdown documentation and natural language prompt patterns without any executable scripts, binaries, or active code logic.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 06:45 PM