The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process untrusted XML sitemap data from external sources.
Ingestion points: The skill reads external XML content using the WebFetch and Read tools during sitemap analysis (Mode 1).
Boundary markers: The instructions do not define delimiters or specific "ignore" markers to prevent the agent from being influenced by malicious text or instructions hidden within XML comments or tags.
Capability inventory: The skill has access to powerful tools including Bash (shell execution), Write (file system modification), and WebFetch (network requests).
Sanitization: There is no specified mechanism for sanitizing or escaping the content of the sitemaps before the agent processes them or uses the data to generate new files like VALIDATION-REPORT.md or sitemap.xml.

seo-sitemap