walgreens-product-data
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves external data such as product descriptions and loyalty messages from the Scavio API. This content is integrated into the agent's context, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Data returned from the
/search,/product,/stores, and/stockendpoints defined in SKILL.md. - Boundary markers: The skill provides instructions to quote promotion and rebate text exactly as written, which acts as a rudimentary delimiter.
- Capability inventory: The skill utilizes network communication through the
requestslibrary and thescavioSDK. - Sanitization: The documentation does not specify any sanitization or filtering of the external product data before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill documentation references the installation of the
scaviolibrary for both Python and Node.js. These are vendor-owned packages used to facilitate communication with the Walgreens data API. - [REMOTE_CODE_EXECUTION]: The MCP configuration utilizes
npxto execute the@scavio/mcp-serverpackage. This is a standard method for running vendor-provided tools in a controlled environment.
Audit Metadata