ClawHub
Back to skill

Security audit

Specter CLI – AI powered startup and deal sourcing

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a legitimate Specter integration, but it documents live delete operations for business/contact data without enough user-control or recovery guidance.

Install only if you trust the Specter CLI source and are comfortable giving it a Specter API key. Treat delete commands as live production actions: confirm resource IDs, prefer least-privileged API credentials if Specter supports them, and avoid letting an agent run deletion commands without explicit human approval.

SkillSpector

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

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents destructive commands such as deleting company lists, people lists, and saved searches without any cautionary note, confirmation guidance, or recovery warning. In an agent skill context, this increases the risk that a user or automated agent will invoke irreversible operations on production Specter data by mistake, especially because the same document mixes read-only and destructive commands together.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.