The Agent Skills Directory

[SAFE]: The skill consists of instructional content and reference templates for performance marketing. It does not contain any executable scripts, non-whitelisted network operations, or hardcoded credentials. All external references are to well-known technology services like Google, Meta, LinkedIn, and TikTok for tracking setup.
[INDIRECT_PROMPT_INJECTION]: The skill instructions include a requirement to read external context files for product marketing information, creating a potential surface for indirect prompt injection if those files are compromised.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md are identified as sources of external context in SKILL.md.
Boundary markers: None specified. The skill does not define specific delimiters or instructions to ignore embedded prompts within these context files.
Capability inventory: The skill's capabilities are limited to generating marketing strategies, ad copy (RSAs), and optimization recommendations. It does not utilize any high-risk tools for shell access, file system writes, or network requests.
Sanitization: None. The skill does not explicitly sanitize or validate the content read from the context files.

ads