backtest-evaluator

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data from external files and incorporates it into agent-generated reports.\n
  • Ingestion points: Data is loaded from files specified by the --state and --csv arguments (e.g., state.json, data.csv).\n
  • Boundary markers: The instructions do not define delimiters or ignore-previous-instruction markers for the content of processed files.\n
  • Capability inventory: The skill uses the Bash tool (run.py) for execution and the Read and Glob tools (SKILL.md) for file access.\n
  • Sanitization: No validation or sanitization of the input data files is performed before processing.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script (run.py) to perform analysis and generate backtest artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:02 AM