cold-email
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructional guidelines for an AI agent to act as a cold email copywriter. It does not contain executable code, scripts, or system commands.
- [SAFE]: The instruction to read a local file
.agents/sales-context.mdis a standard pattern for context-sharing within agent environments and does not facilitate unauthorized data exfiltration. - [SAFE]: References to external tools and services (e.g., Google Postmaster Tools, MXToolbox, Instantly, Lemwarm) are mentions of well-known industry services related to the skill's primary purpose of email deliverability and do not represent a security risk.
- [SAFE]: No prompt injection techniques or attempts to bypass safety filters were identified in the instruction set.
Audit Metadata