shareholder-risk-check
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to run local shell commands for environment setup and data retrieval, specifically calling scripts from a related repository (../findata-toolkit-cn/scripts/views_runner.py).
- [EXTERNAL_DOWNLOADS]: The skill manages its environment by installing Python dependencies via pip from a local requirements file.
- [PROMPT_INJECTION]: The skill processes untrusted external data (company announcements and shareholder information) which presents an indirect prompt injection surface.
- Ingestion points: Data retrieved from external financial providers via views_runner.py.
- Boundary markers: Absent; the skill does not use specific delimiters to separate fetched data from instructions.
- Capability inventory: The skill has the capability to execute shell commands and Python scripts.
- Sanitization: No explicit sanitization or validation of the fetched data is performed before analysis.
Audit Metadata