skills/mnhkahn/cyeam-mcp/roadbook-csv/Gen Agent Trust Hub

roadbook-csv

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the curl binary to send formatted CSV data to a remote server. This is the core mechanism for generating the roadbook.
  • [EXTERNAL_DOWNLOADS]: The skill transmits itinerary data including locations, dates, and notes to the external domains cyeam-open-main-d02895c.d2.zuplo.dev and www.cyeam.com. These endpoints belong to the vendor's service and are used to store and visualize the trip data.
  • [PROMPT_INJECTION]: The skill processes natural language travel plans and formats them into CSV rows. It lacks explicit boundary markers or delimiters for the user-supplied data, which creates a surface for indirect prompt injection. However, the risk is limited by the structured nature of the CSV conversion and the specific tool capabilities available (Low severity).
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by requiring the CYEAM_API_KEY to be provided via environment variables rather than hardcoding it or requesting it in plain text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:35 PM
Security Audit — agent-trust-hub — roadbook-csv