kroger-grocery-data
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references specific versions of the vendor's own software development kits (
scaviofor Node.js and Python) and a Model Context Protocol (MCP) server (@scavio/mcp-server). These are standard library dependencies for the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Kroger banner websites via the Scavio API), which could theoretically contain malicious instructions.
- Ingestion points: Data including product descriptions, nutrition facts, ingredients, allergens, and coupon details are ingested from
api.scavio.dev(SKILL.md). - Boundary markers: The instructions guide the agent to extract specific structured fields and return only what the API provided, although explicit delimiters for external content are not specified.
- Capability inventory: The skill's capabilities are limited to network requests for data retrieval and display; no high-privilege capabilities such as file system writes or arbitrary command execution are present.
- Sanitization: There are no explicit instructions for sanitizing or escaping the retrieved external content before it is presented to the user or processed by the agent.
Audit Metadata