The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites which may contain hidden instructions intended to override agent behavior.
Ingestion points: The scripts/fetch_page.py script fetches HTML data from external URLs.
Boundary markers: SKILL.md and references/skill-contract.md include instructions to ignore instructions embedded in scraped content.
Capability inventory: The skill has network read capabilities via scripts/fetch_page.py and file write access through scripts/generate_markdown_report.py, scripts/generate_pdf_report.py, and scripts/schema_generator.py.
Sanitization: Metadata is extracted via regular expressions, but raw content ingestion creates a potential attack surface.

seo-ecommerce