nordstrom-product-data

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to download and install the vendor's SDKs and server tools from official registries. Evidence: Includes pip install scavio==0.37.0, npm install scavio@0.37.0, and npx -y @scavio/mcp-server@0.35.0 in SKILL.md. These resources are verified as belonging to the skill's author context.
  • [COMMAND_EXECUTION]: The documentation provides multiple shell and code-based execution examples to demonstrate API interactions. Evidence: Contains numerous curl POST examples, a Python implementation script, and Node.js code snippets in SKILL.md for fetching product and store data.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data which could potentially contain adversarial instructions. Evidence:
  • Ingestion points: Product reviews, feature lists, fit notes, and AI-generated review summaries fetched from the Nordstrom API (SKILL.md).
  • Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for the external content.
  • Capability inventory: The skill has the capability to perform network requests to api.scavio.dev to retrieve this data.
  • Sanitization: No specific sanitization or filtering of the retrieved content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 02:36 AM