analytics
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local configuration files to provide context-aware analytics recommendations. This represents a standard surface for indirect prompt injection via untrusted local files.
- Ingestion points: The skill reads
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdat runtime (SKILL.md). - Boundary markers: No specific delimiters or "ignore" instructions are defined for the ingested context files.
- Capability inventory: The skill primarily generates informational content, tracking plans, and implementation scripts (JavaScript/HTML).
- Sanitization: Not explicitly defined for the ingested context data.
- [EXTERNAL_DOWNLOADS]: The documentation includes implementation examples for common analytics services.
- Evidence: Provides template code that references official libraries, such as the Facebook Pixel script at
https://connect.facebook.net/en_US/fbevents.js(references/gtm-implementation.md).
Audit Metadata