content-monetization
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from multiple sources, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill ingests data from external financial APIs (yfinance, AKShare, Wind, SEC EDGAR) and monitors social engagement data (upvotes, comments, shares) from Moltbook.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed data are documented.
- Capability inventory: The agent uses Python scripts for file generation (ebooklib, matplotlib), performs network operations to fetch data, and generates content for platform publication.
- Sanitization: The instructions do not specify any validation or sanitization protocols for data retrieved from external financial databases or user comments.
- [EXTERNAL_DOWNLOADS]: The skill documentation indicates reliance on external data providers and AI services.
- Data Sources: Fetches financial and corporate data from yfinance, AKShare, and SEC EDGAR.
- AI Services: Utilizes external APIs for image generation (DALL·E via ChatGPT or DashScope) and PPT generation (Tongyi Qianwen).
- [COMMAND_EXECUTION]: The skill describes an automated workflow involving local code execution.
- Execution method: Uses Python scripts to format data into Kindle-compatible EPUB files and generate financial charts using matplotlib.
- Automation: Mentions a daily cron job at 11:00 for narrative generation and posting tasks.
Audit Metadata