freshservice-automation
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's core workflows explicitly call FRESHSERVICE_LIST_TICKETS and FRESHSERVICE_GET_TICKET to fetch ticket fields including "description" and "conversations" (user-generated HTML/text) and then use those results to drive follow-up actions (listing, selecting, and bulk updates), which exposes the agent to untrusted third‑party content from Freshservice tickets.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires adding and using the MCP server at https://rube.app/mcp at runtime (RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS), which supplies tool schemas that directly determine the agent's available instructions and behavior.
Audit Metadata