Social Proof Optimizer

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only marketing guidance skill with persuasion risks that are disclosed and mostly bounded by authenticity and compliance checks.

Install only if you want help reviewing or drafting social-proof marketing materials. Limit file access to relevant campaign, landing-page, testimonial, and review documents, and require human approval before publishing claims. Do not use it to invent testimonials, inflate user counts, hide paid endorsements, or create misleading scarcity or demand signals.

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 (3)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The skill description is extremely broad and covers nearly any persuasion, trust-signal, or marketing activity, which can cause an agent to invoke this skill outside its intended niche. In practice, that increases the chance the agent applies psychologically manipulative guidance, including risky social-proof tactics, in contexts where ordinary marketing, compliance, or ethics review would be more appropriate.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The 'Typical triggers' section lacks boundaries and does not tell the agent when not to use this skill, so routine marketing tasks may be routed here unnecessarily. Because the skill contains operational advice on influence, scarcity, herd behavior, and manufactured-proof concepts, over-invocation expands exposure to manipulative recommendations and weakens task separation between ethical auditing and persuasive design.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: This section documents concrete methods for manufacturing social proof, including staged testimonials, fake lines, seeded tip jars, and betting manipulation, but presents them as operational examples without adjacent warnings, ethical boundaries, or abuse-prevention guidance. In the context of a skill explicitly intended to optimize persuasion, that omission materially increases misuse risk by making deceptive influence tactics easier to adopt as actionable playbooks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal