detect-atr-squeeze-regime
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [Data Exposure & Exfiltration] (LOW): The monitoring workflow includes a
--webhookparameter that allows the agent to send analysis results and status changes to an external URL. This is a functional feature but provides a mechanism for data transmission to arbitrary endpoints. - [Unverifiable Dependencies & Remote Code Execution] (LOW): The skill fetches market data from external sources (Yahoo Finance and Stooq). While these are standard financial data providers, the skill relies on these external network connections for its primary functionality.
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from external financial APIs and CSV files to generate reports, which is a common surface for indirect prompt injection.
- Ingestion points:
references/data-sources.md(yfinance API, Stooq CSV downloads). - Boundary markers: The skill uses structured templates (JSON/Markdown) to delimit output.
- Capability inventory: Executes local Python scripts via subprocess and performs network GET requests.
- Sanitization: There is no evidence of input validation or sanitization for the fetched financial data before it is interpolated into templates.
Audit Metadata