The Agent Skills Directory

[DATA_EXFILTRATION]: The skill accesses sensitive local configuration files, including brand profiles and SOPs located at ~/.claude-marketing/brands/{slug}/profile.json and ~/.claude-marketing/sops/. While this is intended for personalizing the audit, it represents a data exposure surface if the agent were manipulated into leaking this information.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Raw HTML source of pages, XML sitemaps, and structured SEO tool exports (CSV/structured data) provided by the user.
Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the processed HTML or XML content.
Capability inventory: The skill has access to local marketing brand configurations and industry compliance rules, though it explicitly states it does not perform HTTP requests or website crawling directly.
Sanitization: There is no mention of sanitizing or escaping the content extracted from the HTML tags or XML entries before it is processed by the agent.

hreflang-check