tracking-crypto-portfolio

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Python scripts via the Bash tool to perform portfolio analysis and data aggregation. This is the primary intended function for calculating valuations.\n- [PROMPT_INJECTION]: Indirect Prompt Injection (Category 8): The skill ingests untrusted data from local JSON portfolio files, which presents a surface for instructions to be embedded in data fields.\n
  • Ingestion points: scripts/portfolio_loader.py reads holdings and metadata from user-provided JSON files.\n
  • Boundary markers: Absent. Output generated by scripts/formatters.py does not use delimiters to wrap processed data.\n
  • Capability inventory: The skill has access to Bash (scoped), Read, and Write tools.\n
  • Sanitization: Absent. The implementation validates data types (e.g., converting quantities to floats) but does not filter or sanitize string content for potential injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 09:32 PM