ClawHub

Salesforce Hardened

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Salesforce CLI helper, but it puts sensitive Salesforce tokens into normal agent workflows without enough containment or redaction guidance.

Review before installing if this agent will have access to real Salesforce orgs, especially production. Use it only with explicit user approval for mutations, deployments, Apex, bulk operations, and raw REST calls. Do not let the agent print or share access tokens, refresh-token-bearing SFDX auth URLs, JWT key contents, or full org-display JSON unless you have a secure redaction and secret-handling process.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Credential Access

High
Category
Privilege Escalation
Content
# List all authenticated orgs
sf org list --json

# Display info about the default org (access token, instance URL, username)
sf org display --json

# Display info about a specific org
Confidence
87% confidence
Finding
access token

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal