personalization-at-scale

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists of prompt instructions and markdown templates for sales research. No executable scripts, network requests, or malicious commands were identified.- [NO_CODE]: No code files, scripts, or package manager configurations are included in this skill.- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes prospect data provided by the user. However, the risk is minimal as the agent's output is restricted to text generation.
  • Ingestion points: Prospect lists and profile details provided to the agent in SKILL.md.
  • Boundary markers: None identified; instructions do not specify how to separate data from instructions.
  • Capability inventory: Limited to text generation for emails and research summaries.
  • Sanitization: No input validation or sanitization instructions are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 10:14 AM