crypto-etl-analytics-core

Warn

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions involve cloning a source code repository from an unverified user on GitHub: https://github.com/Jad-srifi/crypto-etl-analytics-core.git.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the mysql-connector-python and matplotlib packages from official public registries.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes data from an external MySQL database.
  • Ingestion points: The extract_candles function in SKILL.md reads and parses cryptocurrency market data from a database.
  • Boundary markers: No delimiters or safety instructions are present to ensure the agent ignores potential commands embedded in the data.
  • Capability inventory: The skill is capable of performing file system writes via plt.savefig and establishing network connections to database services.
  • Sanitization: While the implementation uses parameterized SQL queries to prevent SQL injection, it does not include sanitization or filtering of the retrieved data content for embedded natural language instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 15, 2026, 08:56 PM
Security Audit — agent-trust-hub — crypto-etl-analytics-core