backtest-diagnose
Warn
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to use the
bashtool to resolve system errors and perform code validation. Specifically, it suggests runningpip installfor missing dependencies and executing Python one-liners for syntax checking. - [EXTERNAL_DOWNLOADS]: The instruction to use
bash("pip install xxx")to fixImportErrorallows the agent to download and install arbitrary packages from external registries, which could lead to the installation of malicious code if the package name is manipulated. - [INDIRECT_PROMPT_INJECTION]: The diagnostic workflow involves reading multiple external files that could be controlled by an attacker or contain untrusted content. This creates a surface where embedded instructions in these files could subvert the agent's logic.
- Ingestion points:
artifacts/metrics.csv,artifacts/equity.csv,artifacts/trades.csv,code/signal_engine.py,config.json, andrun_card.jsonare all read into the agent's context. - Boundary markers: The instructions do not define delimiters or specific markers to separate these file contents from the agent's internal logic.
- Capability inventory: The agent has access to
bashfor command execution,edit_filefor source code modification, andrefresh_strategy_evidencefor state updates. - Sanitization: No evidence of input validation or sanitization is present before the data is used to decide on code edits or shell commands.
- [DYNAMIC_EXECUTION]: The skill uses a shell command to execute Python code at runtime (
python -c "import ast; ...") to validate the Abstract Syntax Tree (AST) of thesignal_engine.pyfile after it has been edited.
Audit Metadata