stock-correlation

Pass

Audited by Gen Agent Trust Hub on Oct 20, 2026

Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_CONTEXT_INJECTION]: The SKILL.md file utilizes a shell command placeholder (!python3 -c "exec(...)") to execute a Python script that checks for the presence and version of the yfinance, pandas, and numpy libraries when the skill is accessed.
  • [COMMAND_EXECUTION]: The skill includes instructions to perform a pip install using subprocess.check_call to ensure all required Python dependencies are available in the execution environment.
  • [EXTERNAL_DOWNLOADS]: The skill fetches and installs well-known data science and finance packages (yfinance, pandas, numpy) from public package registries during its setup phase.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes data retrieved from Yahoo Finance via the yfinance library.
  • Ingestion points: Financial price data and company metadata are downloaded using yf.download() and yf.Ticker().info in SKILL.md and references/sector_universes.md.
  • Boundary markers: No specific delimiters are used to wrap the external data to prevent the model from interpreting content as instructions.
  • Capability inventory: The skill can execute shell commands via subprocess (for installation) and performs network requests to Yahoo Finance APIs.
  • Sanitization: The skill does not perform sanitization on the external data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 20, 2026, 06:43 AM