The Agent Skills Directory

[SAFE]: The skill provides only markdown-based instructions and reference materials for SEO strategy. There is no code, automation script, or command execution included in the files.
[DATA_EXPOSURE]: The instructions direct the agent to check for a local file at .claude/product-marketing-context.md. This is a common pattern for obtaining project context and does not involve unauthorized access to sensitive system files or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided keyword patterns and data sources (ingestion point) without explicit boundary markers or input sanitization. However, a capability inventory across all files confirms there are no subprocess calls, execution tools, file-writing capabilities, or network operations, meaning the attack surface is not exploitable and the risk is safe.

programmatic-seo