analyse-smartmoney-13d
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches filing data from official U.S. government websites, specifically sec.gov and efts.sec.gov. These are recognized as trusted and well-known services.
- [COMMAND_EXECUTION]: The skill executes local TypeScript scripts (watch.ts, score.ts, and tier.ts) via Node.js to perform scoring and tiering logic. These operations are standard functional components of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external SEC filings. Ingestion points: Data enters the system via EDGAR full-text search results. Boundary markers: The instructions explicitly prohibit data fabrication and mandate the use of [UNAVAILABLE] for missing fields, reducing injection risk. Capability inventory: The skill can execute local scripts and write to a designated local cache directory. Sanitization: Data is structured into JSON formats before being passed to the processing scripts, providing a layer of validation.
Audit Metadata