The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands to activate a virtual environment (source ../../.venv/bin/activate) and run scripts from a sibling directory (python ../findata-toolkit-cn/scripts/views_runner.py). This allows the agent to execute code located outside the skill's own directory structure.\n- [EXTERNAL_DOWNLOADS]: The instructions include running pip install -r ../findata-toolkit-cn/requirements.txt, which downloads and installs third-party Python packages from public registries at runtime, introducing risks associated with unverifiable dependencies.\n- [CREDENTIALS_UNSAFE]: The documentation mentions the use of XUEQIU_TOKEN as an environment variable for accessing financial data APIs. While the token itself is not hardcoded, the instruction guides the agent to use and potentially expose sensitive authentication credentials in the execution environment.

equity-research-orchestrator