The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill includes a troubleshooting command that explicitly displays a sensitive API key to the terminal. Evidence: grep "DEEPSEEK_API_KEY" ~/.env.aitrader in the 'DeepSeek API Failure' section.
[DATA_EXFILTRATION]: The skill accesses a sensitive environment configuration file located at ~/.env.aitrader which is used to store credentials and environment variables for the trading system.
[COMMAND_EXECUTION]: The skill executes various local scripts that perform system-level tasks. Evidence: Execution of scripts/diagnose.py with the --update and --restart flags. Evidence: Execution of scripts/smart_commit_analyzer.py which uses dynamic rules derived from git history.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to the processing of untrusted external data. * Ingestion points: Market data and sentiment data fetched by scripts/diagnose.py and processed by Bull/Bear/Judge agents. * Boundary markers: No delimiters or specific instructions to ignore embedded commands are present. * Capability inventory: The skill has the ability to execute shell commands and Python scripts. * Sanitization: No evidence of sanitization or validation of the external data before it is processed by the AI agents.

diagnose