Talkdesk

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This Talkdesk skill is broadly coherent, but it gives an agent raw authenticated API access that can change or delete business data without clear confirmation safeguards.

Review before installing if this will connect to a production Talkdesk account. Prefer Membrane prebuilt actions, avoid raw proxy calls unless necessary, and require explicit confirmation before any POST, PUT, PATCH, or DELETE request.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill explicitly documents raw proxy requests with mutating methods like POST, PUT, PATCH, and DELETE, but does not require confirmation, read-only defaults, or warnings about destructive effects. In an agent setting, this increases the chance of unintended record modification or deletion in a live Talkdesk environment, especially when the model falls back to direct API calls instead of safer prebuilt actions.

VirusTotal

62/62 vendors flagged this skill as clean.