The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several internal Python scripts (e.g., fetch_page.py, parse_html.py, dataforseo_merchant.py) to perform its analysis. These scripts are invoked with user-supplied URLs or keywords to automate the SEO auditing process, which is standard behavior for this type of tool.
[EXTERNAL_DOWNLOADS]: The skill fetches content from external websites via user-provided URLs to analyze on-page SEO signals and product schema. This is the primary function of the skill and is handled via dedicated scripts.
[PROMPT_INJECTION]: As the skill ingests raw HTML from untrusted external sources, it is subject to indirect prompt injection risks. However, the analysis is scoped to specific SEO elements (metadata, headers, schema), which inherently limits the effectiveness of instructions hidden in processed data. This risk is common to all web-auditing tools and is considered acceptable for the stated use case.
Ingestion points: scripts/fetch_page.py retrieves content from arbitrary URLs provided by the user.
Boundary markers: No explicit delimiters are specified in the instructions for the parsed content.
Capability inventory: The skill can read network content, execute local analysis scripts, and communicate with the DataForSEO API.
Sanitization: Content is passed through scripts/parse_html.py, which targets specific SEO elements rather than general text processing.

seo-ecommerce