cold-email-personalization
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of textual instructions, configuration examples, and email templates for outreach. It does not contain any executable scripts, sensitive data access, or unauthorized communication patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data from websites and LinkedIn to personalize emails, which creates an attack surface for malicious instructions embedded in web content. Ingestion points: Prospect information gathered via WebSearch and WebFetch tools. Boundary markers: None provided in the instruction set. Capability inventory: The skill is focused on text generation for emails and does not have shell or code execution capabilities. Sanitization: The skill does not define methods for sanitizing or validating external content before processing.
Audit Metadata