outreach-personalization
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows established business logic for sales automation, focusing on data verification and message generation without requesting excessive privileges or performing unauthorized actions.
- [DATA_EXFILTRATION]: The instructions incorporate specific 'Privacy Rules' that command the agent to mask personally identifiable information (PII), such as names and emails, in its output. This reduces the risk of accidental data exposure.
- [EXTERNAL_DOWNLOADS]: The skill references an official URL from Lusha's public library for sales plays. As Lusha is a well-known service provider, this reference is documented neutrally as a safe informational resource.
- [PROMPT_INJECTION]: The skill processes user-provided contact data and signals. While this presents a surface for indirect prompt injection, the risk is low because the agent's capabilities are restricted to text output following a strict template, with no access to sensitive system tools or execution environments.
Audit Metadata