analytics-tracking
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes external project context to tailor its analytics recommendations. Ingestion points: Instructs the agent to read .claude/product-marketing-context.md if available to gain business and technical context. Boundary markers: The skill does not define specific delimiters or instructions to ignore potential malicious content within the ingested context file. Capability inventory: The skill's functionality is limited to providing information and code templates; it does not perform sensitive operations like file writing or arbitrary command execution. Sanitization: Ingested context is used directly for guidance without sanitization logic.
- [EXTERNAL_DOWNLOADS]: The skill references official integration scripts for well-known analytics platforms. The Google Tag Manager implementation guide (references/gtm-implementation.md) includes the standard Facebook Pixel integration code, which loads a script from Meta's official infrastructure.
Audit Metadata