whale-hunting

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: Comprehensive analysis of the skill's metadata, instructions, and source code revealed no malicious patterns, obfuscation, or safety bypass attempts.\n- [COMMAND_EXECUTION]: The skill utilizes a local Python script (whale_hunting.py) to handle data processing and user arguments, which is a standard and expected implementation for a data analysis skill.\n- [CREDENTIALS_UNSAFE]: The skill follows security best practices by requiring an environment variable (MASSIVE_API_KEY) for API authentication instead of hardcoding sensitive credentials.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided ticker symbols as data inputs for its analysis functions. The inputs are sanitized and used as parameters, presenting no risk of prompt or command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 10:28 AM
Security Audit — agent-trust-hub — whale-hunting