The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (github.com/coreyhaines31/marketingskills) for its tools registry and integration guides. These links point to informational Markdown files that describe how to implement email sequences using third-party services.
[INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted data from user requests and external marketing context files, creating a potential surface for prompt injection.
Ingestion points: User intent/context in SKILL.md and external context files such as .agents/product-marketing.md.
Boundary markers: None defined; the skill lacks specific delimiters to separate user data from instructions.
Capability inventory: The skill is limited to text generation and instruction routing. No executable scripts, subprocess calls, file-write operations, or network requests are present in SKILL.md or the references/ directory.
Sanitization: No input sanitization or validation logic is implemented.
[DATA_EXPOSURE]: The skill instructions direct the agent to read local files (e.g., .agents/product-marketing.md) to gain marketing context. This is a standard practice for personalizing generated content and does not involve accessing sensitive system credentials or private keys.

emails