The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources like Google Search Console, marketplace reports, and customer reviews in SKILL.md, which creates an attack surface for indirect prompt injection. Ingestion points: Untrusted data enters the context through keyword expansion and evidence triage phases described in SKILL.md. Boundary markers: There are no explicit instructions or delimiters mentioned to isolate external content from the agent's internal reasoning. Capability inventory: The skill is configured with Read, Grep, and Bash tool permissions. Sanitization: The skill implements a logical 'Evidence Quality Ladder' and intent validation rules to verify the provenance and reliability of search data before it is actioned.
[EXTERNAL_DOWNLOADS]: The skill references official help documentation and research publications from Amazon, Google, Etsy, and Shopify in SKILL.md to ground its research methodology.

keywords