crypto-ta-analyzer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The CLAUDE.md testing instructions facilitate downloading data from api.coingecko.com. While relevant to the skill, the example code explicitly disables SSL certificate verification (ssl.CERT_NONE), which is a poor security practice that exposes the data fetch to Man-in-the-Middle (MITM) attacks.
  • [COMMAND_EXECUTION] (LOW): The documentation provides a python3 -c one-liner for testing. While this is a standard developer practice, executing arbitrary strings via shell is a capability that should be monitored.
  • [PROMPT_INJECTION] (LOW): Category 8: The skill ingests untrusted market data from an external API via scripts/coingecko_converter.py. There is a theoretical surface for indirect prompt injection if the agent interprets malicious data in the price fields as instructions. \n
  • Ingestion points: scripts/coingecko_converter.py (prepare_analysis_data). \n
  • Boundary markers: Absent. \n
  • Capability inventory: Restricted to numeric computation using numpy and pandas. No high-risk file-write or network-send capabilities based on processed data. \n
  • Sanitization: Uses standard json.loads parsing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:50 PM