The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands including curl, grep, sed, sort, and uniq to analyze website structure, headers, and metadata. These commands are scoped to technical SEO analysis of target URLs or local source files.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to execute external auditing tools.
lighthouse: A well-known performance and SEO auditing utility provided by Google.
structured-data-testing-tool: A standard utility for validating JSON-LD schema markup.
[INDIRECT_PROMPT_INJECTION]: The skill fetches and analyzes content from external websites and local codebases, creating a potential surface for indirect prompt injection.
Ingestion points: External site content is retrieved via curl commands, and local source code is read using grep within the src/ directory.
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the content it audits.
Capability inventory: The skill has access to shell execution (curl, npx, grep) and file system reads.
Sanitization: There is no evidence of explicit content sanitization or filtering applied to external data before analysis.

seo-rank