chewy-product-data
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted data from an external API, such as product descriptions, specifications, and ingredient lists. This data could potentially contain malicious instructions aimed at influencing the agent's behavior.
- Ingestion points: Data entering the context from the /search and /product endpoints, specifically fields like 'description', 'key_benefits', and 'details'.
- Boundary markers: No delimiters or explicit warnings are provided to instruct the agent to ignore instructions embedded in the API data.
- Capability inventory: The skill uses network operations to fetch data but does not explicitly request file system or subprocess execution privileges in its configuration.
- Sanitization: There is no evidence of content sanitization or validation for the returned text fields.
- [EXTERNAL_DOWNLOADS]: The skill suggests the installation of the 'scavio' library via pip and npm, as well as the use of an MCP server via npx. These are vendor-owned tools intended for use with the Scavio API.
Audit Metadata