valuation-regime-detector

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute Python scripts (e.g., views_runner.py) from a relative path (../findata-toolkit-cn/scripts/) to perform financial data queries.\n- [EXTERNAL_DOWNLOADS]: The skill performs automated package installation via pip from a requirements file located in a sibling directory outside the skill's local scope.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and summarizes external financial data from third-party sources.\n
  • Ingestion points: External financial metrics (PE, PB, GDP) fetched via views_runner.py (AKShare data).\n
  • Boundary markers: None identified in the instructional content.\n
  • Capability inventory: Shell command execution (Python script execution).\n
  • Sanitization: No specific sanitization or validation of the retrieved financial data is described prior to summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:23 AM