ClawHub
Back to skill

Security audit

evez-osint-engine

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent about its purpose, but that purpose is high-stakes suspect profiling without visible safeguards.

Install only if you have a lawful, audited process for handling sensitive investigative data. Treat any generated probabilities or priorities as speculative analysis, not evidence or a basis for action without independent verification, documented provenance, bias review, and human oversight.

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
97% confidence
Finding
The skill explicitly supports building suspect networks, computing crime probabilities, and generating intervention-priority reports about identifiable people, including police officers, without any warnings, safeguards, or limits on use. This is dangerous because it encourages high-stakes profiling and decision support that can affect liberty, employment, reputation, or civil rights despite the underlying OSINT and 'eigenforensic' scoring being error-prone, biased, or unverifiable.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.