tw-stock-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of analytical frameworks and instructions for interpreting financial metrics without any embedded shell commands, scripts, or persistent mechanisms.
  • [SAFE]: External URLs referenced (mops.twse.com.tw, twse.com.tw, goodinfo.tw) are official government portals or well-known financial information services in the Taiwan market.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for processing untrusted financial data. 1. Ingestion points: External data from financial reporting sites and user-specified stock symbols (SKILL.md). 2. Boundary markers: None defined. 3. Capability inventory: Framework is limited to data analysis; no tools for file system modification, remote code execution, or network exfiltration are present in the skill definition. 4. Sanitization: None present. Given the lack of impactful tools, this represents a low-risk analytical surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 03:41 AM
Security Audit — agent-trust-hub — tw-stock-analysis