linkfox-keepa-product-series
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Amazon product metadata such as price history, BSR trends, and ratings retrieved from the Keepa API. This external content serves as an ingestion point for untrusted data that could theoretically contain malicious instructions.
- Ingestion points: Data is fetched via
scripts/keepa_product_history.pyfrom thetool-gateway.linkfox.comAPI. - Boundary markers: The instructions do not define strict delimiters or clear "ignore embedded instructions" directives for the processing of this external data.
- Capability inventory: The skill possesses capabilities for network operations, local file system writes in the project directory, and command execution via Python scripts.
- Sanitization: The skill parses data as JSON and implements a summarization strategy for large payloads (exceeding 8KB) to limit the volume of untrusted data entering the agent's context.
- [COMMAND_EXECUTION]: The skill relies on the execution of local Python scripts,
scripts/keepa_product_history.pyandscripts/onboarding.py, to perform data retrieval, caching, and account management tasks. - [EXTERNAL_DOWNLOADS]: The skill initiates network requests to vendor-owned domains (subdomains of
linkfox.com) to fetch product data, handle user authentication (login/SMS), and manage billing. These communications are essential for the skill's primary functionality.
Audit Metadata