a-stock-market

Fail

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The README.md file contains installation instructions that require administrative privileges to create a symbolic link in a system directory, granting the script global execution capabilities.
  • Evidence: sudo ln -sf ~/.openclaw/workspace/skills/a-stock-market/a-stock.py /usr/local/bin/a-stock in README.md
  • [EXTERNAL_DOWNLOADS]: The skill fetches real-time stock data from Tencent Finance's official API. This is a well-known service used according to the skill's primary purpose.
  • Source: https://qt.gtimg.cn/q={symbol}
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external API and prints it to the console, creating a potential surface for indirect instruction injection.
  • Ingestion points: a-stock.py (via urllib.request.urlopen)
  • Boundary markers: Absent; the data is interpolated directly into printed strings.
  • Capability inventory: The skill is limited to terminal output and does not have system-write or dynamic code execution capabilities.
  • Sanitization: The script parses the response using specific delimiters and converts price-related fields to float types, providing basic validation of the input data.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 15, 2026, 10:45 AM
Security Audit — agent-trust-hub — a-stock-market