The Agent Skills Directory

[SAFE]: The skill is designed for mobile SEO auditing, performing legitimate checks on viewport meta tags, layout widths, and interactive target geometry.
[COMMAND_EXECUTION]: The skill utilizes a local script for HTML parsing verification (node ${CLAUDE_SKILL_DIR}/../../scripts/parse-html.mjs). This script is accessed via a relative path within the skill's environment, representing standard usage of internal utility tools.
[PROMPT_INJECTION]: The skill processes untrusted data from external web pages, creating a surface for indirect prompt injection.
Ingestion points: The skill reads raw_html and rendered_dom from the PageSnapshot (SKILL.md).
Boundary markers: No delimiters or explicit instructions to ignore embedded content are defined.
Capability inventory: The skill has access to Bash, WebFetch, Read, Grep, and Glob (SKILL.md).
Sanitization: No specific sanitization or filtering of external content is described.

seo-mobile