The Agent Skills Directory

[DATA_EXPOSURE]: The skill is designed to read project-specific context from local files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md. This is a routine operation for context-aware AI agents to avoid redundant questioning and provide relevant marketing advice. There are no network operations or exfiltration patterns present.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection as it reads content from the aforementioned marketing context files. While these files could theoretically contain malicious instructions if the project environment is compromised, this is a standard capability for this use case and the risk is considered low within the agent's operating environment.
[SAFE]: The skill contains no executable code, remote dependencies, or obfuscated content. It functions primarily through natural language instructions and a static reference library of marketing tactics.

marketing-ideas