ClawHub
Back to skill

Security audit

Negotiation

Security checks across malware telemetry and agentic risk

Overview

This is a text-only negotiation coaching skill with some persuasion tactics that require ethical use, but no hidden execution, data access, persistence, or exfiltration behavior was found.

Install this only if you want negotiation coaching. Use it for lawful, consensual, good-faith bargaining, and avoid using its pressure or leverage tactics to exploit vulnerable people, private information, distress, employment precarity, legal exposure, medical decisions, or personal crises.

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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This section explicitly recommends tactics that shape a counterpart’s behavior through psychological pressure and misdirection, but provides no ethical guardrails, consent boundaries, or warning against deceptive use. In a general-purpose agent skill, that omission can normalize manipulative conduct in sensitive contexts such as workplace disputes, personal relationships, or vulnerable users, increasing risk of coercive or exploitative outcomes.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The content encourages uncovering and leveraging hidden motivations, constraints, and unguarded disclosures as tactical advantage without caution about privacy, fairness, or misuse. In skill form, this can enable social-engineering-style behavior by teaching users to extract sensitive information and exploit asymmetries rather than negotiate in good faith.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.