analytics-setup

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown and templates for setting up analytics properties. It does not contain any executable code, command-line operations, or network exfiltration logic.
  • [INDIRECT_PROMPT_INJECTION]: Section 8 of the skill provides prompt templates for an agent to perform analytics tasks by interacting with external website code and CSS classes. This identifies a surface for indirect injection if the processed website content were malicious. Ingestion points: Website source code and CSS class name rules (SKILL.md). Boundary markers: None provided in the suggested templates. Capability inventory: The skill assumes the agent has access to GTM APIs and the site's code repository (SKILL.md). Sanitization: Not specified in the guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 06:46 AM
Security Audit — agent-trust-hub — analytics-setup