Negotiation

Security checks across malware telemetry and agentic risk

Overview

This is a text-only negotiation coaching skill; its persuasive advice needs ethical use, but the artifacts described do not show hidden execution, data access, persistence, or exfiltration.

Install only if you want negotiation coaching. Use it for lawful, consensual, good-faith bargaining, and avoid applying pressure tactics in abusive relationships, crises, medical or legal decisions, employment precarity, or conversations involving vulnerable people.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (2)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The skill description is broad enough to trigger on generic requests about difficult conversations, salary discussions, objections, or negotiation-adjacent topics, which can cause the agent to invoke persuasive tactics in contexts the user did not explicitly frame as negotiation. In sensitive situations, that expands the chance of manipulative advice being offered without sufficient contextual checks or user intent verification.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill teaches tactical influence methods such as mirroring, accusation audits, calibrated questions, and silence as leverage, but provides no warning about ethical use, consent, or limitations for vulnerable or high-stakes contexts. That omission makes it easier for users to apply psychologically manipulative techniques in coercive, deceptive, or otherwise harmful conversations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal