macro-liquidity

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to perform macro-financial analysis using publicly available data. Its instructions are focused on defining a structured analytical framework and output template.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch data from well-known financial sources such as the New York Fed (newyorkfed.org) and TradingView. These references are documented neutrally as they pertain to the skill's core analytical purpose.
  • [PROMPT_INJECTION]: No evidence of malicious prompt injection, behavior overrides, or safety filter bypasses was found. The instructions are purely functional and domain-specific.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it processes untrusted data from web search results without explicit boundary markers. Ingestion points: Web search results for Fed data, SOFR rates, MOVE index, and Yen carry trade signals (SKILL.md). Boundary markers: Absent; the agent is not explicitly told to ignore instructions within search results. Capability inventory: The skill is limited to the web_search tool and generating a text report. It does not utilize code execution (exec/eval), file system writes, or direct network requests outside of search. Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 10:03 AM