whale-hunting

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (whale_hunting.py) using the uv tool or standard Python. This script processes ticker symbols and arguments provided by the user.- [EXTERNAL_DOWNLOADS]: The skill retrieves financial data from Yahoo Finance and the Massive API to perform its analysis. These are well-known financial data services.- [PROMPT_INJECTION]: There is a surface for indirect prompt injection as the skill processes and displays data from external APIs.
  • Ingestion points: Data enters through the whales_hunter function which fetches external option chain data.
  • Boundary markers: The agent is instructed to render the final results in structured Markdown tables.
  • Capability inventory: The skill is authorized to execute its own internal analysis script via the shell.
  • Sanitization: The script performs standard data rounding and type conversion, though it does not explicitly filter for natural language instructions embedded within API data fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 05:04 AM