ClawHub
Back to skill

Security audit

Lead Contact Finder

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Prismfy-powered contact-search helper, with expected external search queries and no evidence of hidden or destructive behavior.

Install only if you are comfortable sending contact-discovery search terms, including person and company names, to Prismfy. Avoid using it for confidential target lists or sensitive outreach research unless that third-party processing is acceptable for your organization.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This script sends user-supplied person, company, domain, role, and geo query data to a third-party Prismfy search API, but the script itself provides no runtime disclosure, consent gate, or minimization warning before transmission. In a contact-discovery skill, that means potentially sensitive identifiers about outreach targets are exported off-host by default, which is a real privacy and data-governance risk even if it is core functionality.

External Transmission

Medium
Category
Data Exfiltration
Content
while (( attempt < max_attempts )); do
    attempt=$((attempt + 1))
    err="$(mktemp)"
    if response="$(curl -m 20 -fsS "$API_URL" \
      -H "Authorization: Bearer $PRISMFY_API_KEY" \
      -H "Content-Type: application/json" \
      -d "$payload" 2>"$err")"; then
Confidence
97% confidence
Finding
curl -m 20 -fsS "$API_URL" \ -H "Authorization: Bearer $PRISMFY_API_KEY" \ -H "Content-Type: application/json" \ -d

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.