fundamental-stock-analysis

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill includes explicit security scope definitions that forbid the handling of credentials, secrets, or arbitrary URL exploration. It restricts web access to ticker-relevant financial data and reputable news sources.
  • [COMMAND_EXECUTION]: Both the main skill file and the reference playbook explicitly prohibit command execution or system discovery tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data (news and financial filings) which represents a theoretical attack surface.
  • Ingestion points: Web retrieval of financial statements and market news (referenced in SKILL.md and playbook.md).
  • Boundary markers: None explicitly defined for raw data input, though output structure is highly regulated.
  • Capability inventory: Limited to web search and retrieval; no file-system write access or subprocess capabilities are requested.
  • Sanitization: Employs a 'Source Hierarchy' (Tier 1-3) and requires cross-checking anomalous metrics against second sources to prevent reliance on potentially poisoned external data.
  • [EXTERNAL_DOWNLOADS]: The skill uses web search for data collection from well-known financial services (SEC.gov, Yahoo Finance, etc.). These are documented as preferred domains for the intended primary purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:17 PM