The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from external websites during the content inventory and brand voice extraction phases.
Ingestion points: Phase 2 (cataloging content) and Phase 6 (fetching blog posts via WebFetch) ingest untrusted data from the internet (SKILL.md).
Boundary markers: The instructions do not define specific boundary markers or warnings to the agent to disregard instructions embedded within the fetched content.
Capability inventory: The skill has the capability to write research reports and data files to the local filesystem (clients/[client]/research/) and execute Python scripts (python3).
Sanitization: No explicit sanitization or filtering of the fetched web content is described before it is processed by the AI.
[COMMAND_EXECUTION]: The skill orchestrates its workflow by executing shell commands to run Python scripts for site cataloging and domain analysis (python3 skills/site-content-catalog/scripts/catalog_content.py and python3 skills/seo-domain-analyzer/scripts/analyze_domain.py).
[EXTERNAL_DOWNLOADS]: The skill fetches SEO performance data from well-known third-party services (Semrush, Ahrefs, Google) using the Apify platform, which requires a user-configured APIFY_API_TOKEN environment variable.

seo-content-audit