The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes Amazon product data (titles, brands, category paths) retrieved from the SellerSprite API. This external content is interpolated into the agent's context for display and competitive analysis, which is a potential surface for indirect prompt injection if the external data contains malicious instructions.
Ingestion points: API response data retrieved in scripts/sellersprite_competitor_lookup.py and presented to the user.
Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore instructions embedded in the external data.
Capability inventory: The skill writes JSON result files to the local project directory and performs network operations to LinkFox API endpoints.
Sanitization: There is no evidence of string validation or sanitization for the API-returned content.
[EXTERNAL_DOWNLOADS]: The skill's scripts reference external library dependencies required for specific functionalities.
scripts/onboarding.py mentions the need for the requests, qrcode, and pillow Python packages for authentication and QR code generation.
[COMMAND_EXECUTION]: The skill relies on executing local Python scripts to interact with the SellerSprite and LinkFox APIs.
Instructions in SKILL.md and references/onboarding.md guide the agent to execute scripts/sellersprite_competitor_lookup.py for product lookups and scripts/onboarding.py for user registration, login, and billing tasks.

linkfox-sellersprite-competitor-lookup