skills/ssheleg/sheleg-dev/ad-tracking/Gen Agent Trust Hub

ad-tracking

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and downloads JavaScript SDKs from well-known technology providers for analytics and advertising purposes:
  • Google Tag Manager: https://www.googletagmanager.com/gtag/js
  • Meta (Facebook) Pixel: https://connect.facebook.net/en_US/fbevents.js
  • LinkedIn Insight Tag tracking endpoints.
  • [SAFE]: The skill uses placeholders such as G-XXXXXXXXXX, AW-XXXXXXXXX, and PIXEL_ID for configuration, correctly identifying them as environment variables or template values rather than hardcoding sensitive credentials.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill is designed to capture and process user-controllable data from URL parameters (UTM parameters, gclid, fbclid) and user profile data (email, name, phone) in SKILL.md and references/meta-linkedin.md.
  • Boundary markers: No specific boundary markers are utilized to delimit these parameters from the agent's internal instructions.
  • Capability inventory: The skill has the capability to transmit this data to external analytics platforms via browser-based events.
  • Sanitization: The implementation follows industry best practices by hashing sensitive personal identifiers (PII) before transmission to external services.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 10:08 AM
Security Audit — agent-trust-hub — ad-tracking