ClawHub
Back to skill

Security audit

GitHunt

Security checks across malware telemetry and agentic risk

Overview

GitHunt is a disclosed recruiting search skill that queries GitHunt's API for GitHub developer profiles, with privacy caveats but no hidden execution or persistence found.

Install only if you are comfortable sending recruiting search criteria to githunt.ai and receiving developer profile/contact data. Treat emails, social handles, hireability, company, and location as personal data; use them only for legitimate, compliant recruiting or research, avoid bulk unsolicited outreach, and retain only what you actually need.

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 (8)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly promotes finding candidates and obtaining contact information, but it provides no privacy notice, lawful-use guidance, or warning about handling personal data. This creates a real privacy/compliance risk because users may collect, enrich, and process personal contact details without clear constraints or consent considerations.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documented response schema includes sensitive contact-related fields such as email, website, Twitter handle, company, and hireability status without any warning about privacy-sensitive handling. Providing these fields in a recruitment/discovery context increases the chance of bulk profiling, unsolicited outreach, or improper retention of personal information.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The script sends user-supplied search parameters such as location, role, and skills to a third-party API, but it does not clearly warn the operator that their input will be transmitted off-host. In a recruiting/search skill, this transmission is functionally expected, but the lack of explicit disclosure creates a real privacy and consent issue, especially in agent contexts where users may not realize their prompts are leaving the local environment.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill description explicitly promises 'contact info' for discovered developers but provides no privacy, consent, or acceptable-use guidance. In a recruiting/outreach context, this can normalize collection and downstream use of personal data without informing users about legal, ethical, or platform-policy constraints.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The response schema includes email, website, and social handles, and the document later suggests outreach automation, yet it omits any warning about personal-data handling, consent, or anti-spam obligations. This creates a concrete risk that integrators will operationalize profiling and contact harvesting in ways that violate privacy expectations or regulatory requirements.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script transmits user-supplied search terms (location, skills, and limit-derived request metadata) to a third-party API without any explicit disclosure, consent prompt, or privacy notice at runtime. In a recruiting/search skill, these inputs may contain sensitive business intent or personal-location targeting data, so silent transmission creates a real privacy and data-governance risk even though the network call is central to the feature.

External Transmission

Medium
Category
Data Exfiltration
Content
echo ""

# Make streaming request and parse SSE
curl -s -N -X POST "$API_URL/rank/users/stream" \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -H "User-Agent: OpenClaw/1.0 (githunt-skill)" \
Confidence
95% confidence
Finding
curl -s -N -X POST "$API_URL/rank/users/stream" \ -H "Content-Type: application/json" \ -H "Accept: text/event-stream" \ -H "User-Agent: OpenClaw/1.0 (githunt-skill)" \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
echo ""

# Make request
response=$(curl -s -X POST "$API_URL/rank/users" \
  -H "Content-Type: application/json" \
  -H "Accept-Encoding: gzip" \
  -d "$payload" --compressed 2>/dev/null)
Confidence
95% confidence
Finding
curl -s -X POST "$API_URL/rank/users" \ -H "Content-Type: application/json" \ -H "Accept-Encoding: gzip" \ -d

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.