The Agent Skills Directory

[PERSISTENCE]: The skill's documentation in references/onboarding.md instructs users to persist their API keys by appending export commands to shell profile files such as ~/.zshrc and ~/.bashrc, or by using the setx command on Windows. These methods modify the environment across sessions to ensure the tool remains authenticated.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Etsy API, which creates a surface for indirect prompt injection attacks.
Ingestion points: Data is received from the Etsy API and processed within scripts/etsy_product_query.py.
Boundary markers: The skill does not implement delimiters or explicit instructions to the agent to disregard potentially malicious content embedded in the product listings.
Capability inventory: The associated scripts perform network operations (call_api in scripts/etsy_product_query.py) and write to the local file system (_save_cache, open(out_path, "w")).
Sanitization: The external content from Etsy is not sanitized or escaped before being written to files or displayed in the session.
[DATA_EXFILTRATION]: The skill's scripts access the user's API key and session identifiers, transmitting them to the vendor's API endpoints (e.g., tool-gateway.linkfox.com, api.linkfox.com, agent-api.linkfox.com) for authentication and account management purposes. This behavior is consistent with the skill's primary function as a service-linked tool.

linkfox-etsy-product-query