gtm-tracking-plan

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill fetches and analyzes data from user-provided URLs, creating a surface for indirect prompt injection where malicious content on a website could attempt to influence the agent's behavior.
  • Ingestion points: Website content is retrieved using the WebFetch tool in the first step to infer event taxonomy and site structure.
  • Boundary markers: The instructions do not define specific delimiters or "ignore instructions" blocks for the data retrieved from external sites.
  • Capability inventory: The skill environment allows access to WebFetch, WebSearch, Bash, Read, and Write tools.
  • Sanitization: No explicit sanitization or filtering of fetched content is described before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 11:31 AM
Security Audit — agent-trust-hub — gtm-tracking-plan