freshdesk-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 required workflows (e.g., FRESHDESK_VIEW_TICKET and FRESHDESK_LIST_ALL_TICKET_CONVERSATIONS in SKILL.md) explicitly fetch and require reading ticket descriptions and conversation bodies (user-generated HTML content from Freshdesk) which the agent uses to decide replies and next actions, exposing it to untrusted third-party content that could carry indirect prompt injections.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill requires adding the MCP endpoint https://rube.app/mcp and uses RUBE_SEARCH_TOOLS at runtime to fetch tool schemas from that server which directly control agent prompts/instructions, so this external URL is a required runtime dependency that affects agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:34 AM