The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references official documentation and resources from well-known services.
Evidence: Links to help.etsy.com, sellercentral.amazon.com, developers.google.com, and help.shopify.com are used for grounding and verification.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process untrusted data from external search reports and competitor listings.
Ingestion points: Untrusted keyword lists and search reports enter the agent context through the keyword research process described in SKILL.md.
Boundary markers: The skill does not explicitly define boundary markers for untrusted input data.
Capability inventory: The skill has access to Read, Grep, and Bash tools.
Sanitization: No specific sanitization or validation logic for the input query data is provided in the instructions.

keywords