equity-pledge-risk-monitor
Warn
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install dependencies from an external source via
python -m pip install -r ../findata-toolkit-cn/requirements.txtas part of its environment setup inreferences/data-queries.md. - [COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands to function, including activating a virtual environment (
source ../../.venv/bin/activate) and running various Python tools using thepythoncommand inreferences/data-queries.md. - [REMOTE_CODE_EXECUTION]: The skill relies on and executes code from a sibling directory (
../findata-toolkit-cn/scripts/views_runner.py) that is not included in the skill's own file distribution. This creates a dependency on external, unverifiable code at runtime. - [INDIRECT_PROMPT_INJECTION]: The skill processes financial data retrieved from external sources (e.g., Eastmoney, Xueqiu) and uses it to generate reports. This represents a potential vulnerability surface where malicious content embedded in the processed financial data could influence the agent's output.
- Ingestion points: Data returned from
views_runner.py(JSON output from financial APIs). - Boundary markers: None explicitly implemented to separate data from instructions.
- Capability inventory: Execution of Python scripts, shell command execution, and file system interactions.
- Sanitization: No specific sanitization or validation of the external API data is described before it is used for analysis.
Audit Metadata