The Agent Skills Directory

[SAFE]: The skill's primary function is to provide data-driven pricing signals for Amazon sellers, which is performed through transparent interactions with its official API.
[EXTERNAL_DOWNLOADS]: The Python script apiclaw.py communicates with https://api.apiclaw.io/openapi/v2. This is a legitimate interaction with the vendor's data infrastructure required for the skill's operation.
[COMMAND_EXECUTION]: The skill uses a local Python script to perform API requests. The script is cleanly written using the Python standard library and does not execute arbitrary or untrusted shell commands.
[DATA_EXPOSURE]: The skill manages API credentials using standard practices, checking for the APICLAW_API_KEY environment variable or a local config.json file. It does not access unrelated sensitive system files.
[PROMPT_INJECTION]: The skill processes external data from Amazon, including product titles and customer reviews. This represents a surface for indirect prompt injection (Category 8).
Ingestion points: Product metadata (titles, features, descriptions) and review text are ingested via the realtime/product and reviews/analysis endpoints in apiclaw.py.
Boundary markers: None. The skill does not currently use explicit delimiters or instructions to ignore embedded commands in the product data.
Capability inventory: The agent uses retrieved data to perform pricing simulations and provide RAISE/HOLD/LOWER signals.
Sanitization: None. Data is passed directly from the API response to the agent context. However, as there are no malicious patterns or high-privilege capabilities, this remains a low-risk surface.

Dynamic Pricing Intelligence Agent