The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites and search results to perform SEO audits and research. This creates a surface where malicious instructions embedded in web content could influence the agent's behavior during report generation.
Ingestion points: The skill utilizes the fetch tool to read external URLs and read_file to access existing site content.
Boundary markers: There are no instructions to use explicit delimiters or 'ignore' directives when processing external content.
Capability inventory: The skill possesses file-system modification tools (write_file, edit_file, create_file) which could be targeted by an injection attack to write malicious content or configurations.
Sanitization: No sanitization or validation logic is specified for the fetched data before it is incorporated into the agent's analysis.

optimize-seo