marketing-plan
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices for secret management by instructing the agent to utilize environment variables (.env files) for API keys rather than hardcoding them within instructions or scripts.
- [COMMAND_EXECUTION]: The skill manages plan artifacts within a dedicated local directory structure (~/marketing-plans/) and utilizes standard git commands for optional publishing of finalized documents to user-specified repositories.
- [SAFE]: Data handling analysis shows that the skill retrieves sensitive business metrics (e.g., revenue from Stripe, traffic from GA4) through authorized Model Context Protocol (MCP) integrations and stores findings locally in the user's workspace for processing.
- [EXTERNAL_DOWNLOADS]: The instructions reference well-known technology tools and services, such as agent-browser and defuddle, which are standard utilities in the agentic ecosystem for web research and data extraction.
- [SAFE]: The skill ingests and analyzes user-provided client materials (such as pitch decks and audits); while this represents an untrusted data ingestion surface, the process is well-defined, transparently documented, and inherent to the skill's primary function of generating customized marketing strategies.
Audit Metadata