cold-email-personalization
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, strategies, and templates for sales outreach. It does not include any scripts, executables, or platform-specific command injections.
- [NO_CODE]: The skill is a 'no-code' skill, meaning it relies purely on natural language instructions and provided documentation to guide the agent's behavior.
- [DATA_EXPOSURE]: While the skill involves researching prospect information, the instructions focus on publicly available data (e.g., LinkedIn posts, company websites, and public reviews). There are no requests for the agent to access sensitive local files, credentials, or private environment variables.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from third-party sources like pricing pages or online reviews. Although this creates a surface for indirect prompt injection, the skill's capabilities are limited to generating email text, and it lacks dangerous tools (like code execution or file system writes) that could be exploited by such an injection.
Audit Metadata