company-analyzer

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.\n
  • Ingestion points: The scripts/fetch_data.sh script fetches the longBusinessSummary (company description) from the Yahoo Finance API.\n
  • Boundary markers: Prompt templates in scripts/run-framework.sh interpolate this data into prompts labeled as 'Raw Data' but lack strict delimiters or system-level instructions to ignore embedded commands.\n
  • Capability inventory: The skill executes local bash scripts and performs network operations via curl.\n
  • Sanitization: No sanitization is performed on retrieved descriptions before LLM processing.\n- [SAFE]: Network operations are limited to well-known and trusted financial data providers including SEC EDGAR, Yahoo Finance, and Alpha Vantage.\n- [SAFE]: No hardcoded secrets were found; API keys are retrieved from local configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:14 PM