analytics-tracking
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest data from .agents/product-marketing-context.md or .claude/product-marketing-context.md. If these files contain malicious instructions, they could influence the agent's behavior.
- Ingestion points: .agents/product-marketing-context.md and .claude/product-marketing-context.md (read via file system tools).
- Boundary markers: No explicit delimiters or warnings are used to distinguish project context from agent instructions.
- Capability inventory: The skill has access to analytics tool integrations as defined in the platform's registry.
- Sanitization: The skill does not describe any validation or filtering of the context file content.
- [EXTERNAL_DOWNLOADS]: The skill documentation includes code snippets that reference external scripts from well-known services.
- Evidence: https://connect.facebook.net/en_US/fbevents.js is included in the Facebook Pixel implementation guide in references/gtm-implementation.md.
Audit Metadata