vcp-screener

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches financial data from the Financial Modeling Prep API (financialmodelingprep.com). This is a well-known and established service for stock market information.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes and displays data retrieved from an external API.\n
  • Ingestion points: Untrusted data such as company names, sectors, and sub-sectors are fetched from the FMP API in scripts/fmp_client.py.\n
  • Boundary markers: The Markdown and JSON reports generated in scripts/report_generator.py use structured headers and tables but do not utilize specific delimiters to isolate potentially malicious text from the API.\n
  • Capability inventory: The skill has permissions to write local report files and perform data analysis calculations. It does not possess network-write capabilities for user data.\n
  • Sanitization: The skill does not perform explicit sanitization or escaping of API-provided strings before including them in the generated reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:37 PM