analyse-orderflow

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches cryptocurrency market data from Coinglass and CME futures charts via the WebFetch tool. These are recognized as well-known and standard services for market microstructure data.
  • [PROMPT_INJECTION]: The skill's architecture for processing external data was analyzed for indirect prompt injection risks. 1. Ingestion points: External content is retrieved from coinglass.com and CME charts. 2. Boundary markers: None present in the instructions. 3. Capability inventory: The skill is strictly analytical and does not possess capabilities for file writing, system command execution, or network exfiltration. 4. Sanitization: No explicit sanitization of external data is performed, but the lack of dangerous tools mitigates the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 02:21 PM
Security Audit — agent-trust-hub — analyse-orderflow