The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external website content, sitemap files, and robots.txt files based on user input. This external data is untrusted and could potentially contain malicious instructions or payloads intended to influence the agent's logic during the audit process.
Ingestion points: The argument-hint and description fields indicate the skill accepts website and sitemap URLs to process external web content.
Boundary markers: The provided SKILL.md does not specify any delimiters or safety instructions to prevent the agent from obeying instructions that might be embedded within the analyzed sitemaps or pages.
Capability inventory: The skill description indicates it cross-checks URLs, validates structure, and reviews robots.txt references, which requires network access and parsing of external data.
Sanitization: There are no instructions in the analyzed file for sanitizing or escaping the content retrieved from external URLs before it is processed by the agent.

sitemap-audit