analytics-tracking
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates an external context file to customize its advice, creating a potential surface for indirect instruction injection.\n
- Ingestion points: The
SKILL.mdfile instructs the agent to read.claude/product-marketing-context.mdif it exists.\n - Boundary markers: No explicit delimiters or instructions to disregard potential commands within the context file are provided.\n
- Capability inventory: The skill generates implementation plans and JavaScript code snippets but does not have capabilities for system-level execution or network exfiltration.\n
- Sanitization: The skill does not define methods for sanitizing the input from the context file.\n- [EXTERNAL_DOWNLOADS]: The documentation includes standard implementation snippets for third-party analytics services.\n
- The guide for Facebook Pixel implementation in
references/gtm-implementation.mdreferences the official library athttps://connect.facebook.net/en_US/fbevents.js.
Audit Metadata