The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/fetch_page.py performs network requests to fetch external HTTP/HTTPS content. It implements security validations to prevent Server-Side Request Forgery (SSRF) by ensuring that IP addresses are global and blocking URLs that contain embedded credentials.
[EXTERNAL_DOWNLOADS]: The scripts/generate_pdf_report.py script suggests the installation of the reportlab library via pip if it is not already available on the system.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web pages, which is a potential vector for indirect prompt injection.
Ingestion points: scripts/fetch_page.py retrieves HTML content from external URLs.
Boundary markers: SKILL.md contains explicit instructions to treat scraped text and third-party exports as untrusted and to ignore any instructions found within that evidence.
Capability inventory: The skill has the ability to perform network requests (scripts/fetch_page.py) and write files to the local file system (scripts/generate_markdown_report.py, scripts/generate_pdf_report.py, scripts/schema_generator.py).
Sanitization: scripts/fetch_page.py uses regex and HTML unescaping to clean extracted text before it is presented to the agent.
[DYNAMIC_EXECUTION]: Several utility scripts (scripts/generate_markdown_report.py, scripts/schema_generator.py) read and write files based on user-supplied paths and perform dynamic data manipulation, such as filling JSON-LD templates.

seo-sxo