ads

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The file references/conversion-tracking.md contains standard JavaScript tracking snippets for well-known advertising services, including Google Ads, Meta Ads, LinkedIn, and TikTok. These scripts are intended for the user to implement on their own web properties for attribution purposes and do not represent unauthorized data exfiltration by the agent. All scripts point to official service domains (e.g., googletagmanager.com, facebook.net, licdn.com, tiktok.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external context from files such as .agents/product-marketing.md. While this is a data ingestion surface, the skill is focused on strategy and copy generation and does not utilize high-privilege tools (such as shell execution or dynamic code evaluation) that would facilitate an exploit through this vector. Proper boundary management is encouraged for the integrated context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 08:49 AM