list-building
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection by processing external LinkedIn data. * Ingestion points: Content from profile pages via read_page. * Boundary markers: None specified. * Capability inventory: Local file system writes and browser navigation. * Sanitization: Content is captured and stored without explicit validation.
- [DATA_EXFILTRATION]: The skill reads and writes to the .business_growth/ directory to manage campaign data and user settings, which is consistent with its stated purpose.
- [EXTERNAL_DOWNLOADS]: The skill navigates to LinkedIn, a well-known and trusted service, to perform its lead-generation tasks.
Audit Metadata