The Agent Skills Directory

[NO_CODE]: The skill package contains no executable scripts or binary files, consisting solely of informational Markdown and YAML configuration.
[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill is designed for SEO auditing and provides static templates for hreflang implementation. It does not attempt to access sensitive data, execute remote code, or bypass AI safety constraints.
[PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection as it processes external web content. Evidence: 1. Ingestion points: External URLs and HTML content provided for auditing (SKILL.md). 2. Boundary markers: No explicit delimiters are defined in the skill instructions. 3. Capability inventory: Limited to generating SEO reports and tag templates; no network or file system write permissions are requested. 4. Sanitization: No sanitization or input validation is described for the analyzed content. This surface is considered safe given the lack of exploitable capabilities.

seo-hreflang