a-share-screener

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • No Code (SAFE): The skill consists solely of a Markdown file (SKILL.md) providing screening strategies and output templates. No executable scripts (Python, Node.js, Shell) are included.
  • Data Privacy & Credentials (SAFE): There are no hardcoded API keys, secrets, or references to sensitive local file paths (such as .env or SSH configs).
  • Command Execution (SAFE): The skill does not attempt to execute system commands, utilize privilege escalation (sudo), or establish persistence.
  • Indirect Prompt Injection (LOW): While the skill suggests using web search to fetch stock data, this is a standard information-retrieval pattern and lacks dangerous capability surfaces like file-write or subprocess-exec that would escalate risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:28 PM