Saleshood

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

Overview

The skill is a coherent Saleshood integration, but it gives an agent broad authenticated API access, including write and delete requests, without clear safeguards.

Install only if you are comfortable letting an agent use your Saleshood account through Membrane. Prefer the listed Membrane actions, and require explicit confirmation before the agent sends POST, PUT, PATCH, or DELETE proxy requests because those may change or remove business data.

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: 81% confidence
• Finding: The skill explicitly documents direct proxying of arbitrary requests to the Saleshood API without pairing that capability with safeguards like confirmation for write operations, endpoint allowlisting, or warnings about sensitive data access and modification. In an agentic setting, this increases the chance of overbroad reads, unintended writes, or misuse of authenticated access through generic request construction.

VirusTotal

63/63 vendors flagged this skill as clean.