industry-board-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run Python scripts located in a sibling directory (
../findata-toolkit-cn/scripts/views_runner.py). These commands are used to discover views, describe schemas, and fetch financial data. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to install Python dependencies using
pip install -r ../findata-toolkit-cn/requirements.txt. While the source is a local sibling directory, it facilitates the installation of third-party packages into the environment. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of external financial data.
- Ingestion points: Data is fetched from external sources like East Money (EM), Tonghuashun (THS), and Xueqiu via the
views_runner.pyscript, as documented inreferences/data-queries.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential malicious content embedded within the fetched financial data.
- Capability inventory: The skill has the capability to execute shell commands and run Python scripts (
SKILL.md,references/data-queries.md). - Sanitization: There is no evidence of sanitization or validation of the external data before it is processed by the agent for analysis.
Audit Metadata