The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of external web content, which introduces a potential attack surface for indirect prompt injection.
Ingestion points: The skill instructs the agent to use web_fetch and curl to retrieve content from external URLs provided by the user for auditing purposes.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the retrieved HTML content.
Capability inventory: The skill itself does not invoke dangerous subprocesses, but the agent using this skill typically possesses capabilities like file writing and shell access which could be targeted by instructions hidden on an audited page.
Sanitization: The skill explicitly notes that the platform's web_fetch tool strips <script> tags during conversion, which provides a layer of protection against client-side script execution.
[SAFE]: The skill references several well-known and trusted external services and tools for SEO analysis (e.g., Google Search Console, PageSpeed Insights, Screaming Frog, Ahrefs, Semrush). These references are informative and represent standard industry practice.

seo-audit