ClawHub
Back to skill

Security audit

Salesflare CRM

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Salesflare CRM helper that can read and change CRM data when given an API key, with documented confirmation and read-only defaults.

Install only if you intend to let an agent use your Salesflare API key. Use a least-privileged key, keep SALESFLARE_BASE_URL on a trusted endpoint, confirm every write/delete with exact record IDs and payloads, and run smoke-test write modes only in a workspace where temporary CRM test records are acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly declares access to an environment secret (`SALESFLARE_API_KEY`) and instructs use of local scripts that perform network requests, but the analyzer indicates these effective capabilities are not reflected as explicit permissions. This mismatch weakens security review and sandboxing because consumers may underestimate that the skill can read secrets, invoke shell/Python, access files, and send authenticated requests to an external API.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The file documents a smoke test mode that performs POST, PUT, and DELETE operations against a live Salesflare environment, but it does not present a prominent safety warning at the point of use about mutating production CRM data. In an agent-skill context, this increases the chance that a user or downstream agent enables write/delete flags in the wrong environment and unintentionally creates, modifies, or removes business records.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.