The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external context files, which represents an indirect prompt injection surface. Instructions embedded in these files could potentially override the agent's behavior during analytics setup.\n
Ingestion points: The skill explicitly checks for and reads .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md.\n
Boundary markers: There are no specific delimiters or instructions provided to the agent to distinguish between data and instructions within these files.\n
Capability inventory: The skill enables the agent to generate JavaScript implementation code for GTM and GA4 and to design tracking plans.\n
Sanitization: No sanitization or verification mechanisms are described for the content of the marketing context files.\n- [EXTERNAL_DOWNLOADS]: The skill references and directs the agent to documentation and tool registries hosted on a third-party GitHub repository that is not part of the trusted vendor list.\n
Evidence: Multiple links point to github.com/coreyhaines31/marketingskills for implementation guides related to GA4, Mixpanel, Amplitude, PostHog, and Segment.

analytics