stock-sector-monitoring
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs news linkage analysis by searching for and summarizing recent market news to explain sector momentum.
- Ingestion points: External news results fetched during the "板块异动+新闻联动分析" (Sector Change + News Linkage Analysis) step in
SKILL.md. - Boundary markers: The instructions do not specify any delimiters or warnings to separate untrusted news content from the agent's internal reasoning.
- Capability inventory: The skill has the ability to write reports to the local file system (
reports/directory) and call thebaoyu-post-to-wechattool to publish content. - Sanitization: There is no evidence of filtering, escaping, or validation of the fetched news content before it is summarized into a report.
- [COMMAND_EXECUTION]: The monitoring script invokes shell commands to manage the terminal display.
- Evidence:
os.system('clear' if os.name == 'posix' else 'cls')inscripts/sector-monitoring.py. - Context: The command is hardcoded to clear the screen during continuous monitoring updates and does not accept user-supplied input, posing no threat of shell injection.
Audit Metadata