13f-watch

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for investment research and follows a "recommend-only" policy, explicitly stating it never executes trades. It focuses on analyzing public financial data from the SEC EDGAR system.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to use a local helper script, watch.py, for deterministic tasks like checking if a ticker has been previously recommended. This script is part of the skill package and handles structured data (JSON/JSONL) without executing arbitrary code or remote scripts.
  • [DATA_EXFILTRATION]: File system access is restricted to reading and writing a local recommendation ledger and a fund manager roster. The data processed consists of public ticker symbols, CIK numbers, and investment metadata, posing no risk to sensitive user information or system credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 08:03 AM
Security Audit — agent-trust-hub — 13f-watch