linkfox-wallysmarter-product-detail
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external product information (titles, descriptions) from Walmart, which constitutes an ingestion point for untrusted data that the agent will handle.
- Ingestion points: The
scripts/wallysmarter_product_detail.pyscript fetches product data from the WallySmarter API and passes it back to the agent. - Boundary markers: Data is passed to the agent context without specific boundary markers or instructions to ignore embedded commands.
- Capability inventory: The skill has file system write access for logging and caching within the
linkfox/directory and network access to the vendor's API gateway. - Sanitization: No explicit sanitization or filtering of the fetched product descriptions is performed before the data is presented to the agent context.
- [SAFE]: The network operations and file system activities, such as logging to the
linkfox/directory and reading theLINKFOX_AGENT_API_KEY, are consistent with the skill's documented functionality and the vendor's provided infrastructure.
Audit Metadata