research-company
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection (Category 8) where external web content could potentially influence agent behavior. • Ingestion points: Data is fetched from company URLs and web search results as defined in SKILL.md. • Boundary markers: No delimiters or specific ignore instructions are present to sequester external data. • Capability inventory: The generate_report.py script uses reportlab Paragraphs which parse and render formatting tags. • Sanitization: The skill lacks explicit sanitization of the fetched data before processing.
- [EXTERNAL_DOWNLOADS]: The skill installs the reportlab package from PyPI, which is a well-known and trusted service for PDF generation.
- [COMMAND_EXECUTION]: The skill uses standard shell commands to manage its environment and execute the included report generation script.
Audit Metadata