petco-product-data
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured product data, ingredients, and reviews from an external API, creating a surface for indirect prompt injection if the source data is compromised.
- Ingestion points: API responses from
https://api.scavio.dev/api/v1/petco/*endpoints (SKILL.md). - Boundary markers: Absent; no specific instructions are provided to the agent to distinguish between data and instructions in API results.
- Capability inventory: The skill utilizes network request capabilities via the
requestslibrary in Python and theScavioSDK in Node.js (SKILL.md). - Sanitization: Not specified; the instructions do not mention filtering or escaping the ingested product data before processing.
- [EXTERNAL_DOWNLOADS]: The skill documentation references official, versioned packages and tools provided by the vendor.
- Evidence: Mentions installation of
scavio==0.33.0(Python),scavio@0.33.0(Node.js), and execution of@scavio/mcp-server@0.31.0via npx. - [REMOTE_CODE_EXECUTION]: The documentation includes a command to execute a remote package for the Model Context Protocol (MCP) server.
- Evidence:
npx -y @scavio/mcp-server@0.31.0(SKILL.md).
Audit Metadata