Security audit

Product Validation Planner

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation-only product validation planner with broad activation wording but no hidden execution, credentials, persistence, or destructive behavior.

Install this if you want lightweight help with product idea validation. Be aware it may activate for fairly general product, startup, SaaS, prototype, or validation requests because the trigger wording is broad; disable implicit invocation or narrow triggers if you want stricter routing.

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 (7)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger sentences are generic enough to match many ordinary product, workflow, or startup-related requests, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of incorrect routing, context hijacking by unrelated prompts, or unintended invocation of downstream instructions that may shape the assistant's behavior when another skill or base behavior would be safer.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad enough that the skill may activate for loosely related requests such as general business, validation, prototype, or startup discussions. This can cause unintended routing, increasing the chance that the agent applies this skill in contexts where its workflow or assumptions are not appropriate, which may lead to incorrect guidance or override more relevant skills.

Vague Triggers

High

Confidence: 95% confidence
Finding: The skill description uses broad terms such as business-and-operations, product idea, validation, prototype, saas, workflow, artifact, checklist, analysis, and implementation support, which can match a very large range of normal user requests. This can cause the skill to activate outside its intended niche, increasing the chance that unrelated conversations are steered by this skill and that more appropriate skills or safeguards are bypassed.

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger keywords and example phrases are highly ambiguous and rely on generic startup and product terms that appear in many benign requests. Because activation appears to depend on loose keyword matching, the skill may be invoked too often or manipulatively, leading to prompt-routing confusion, unintended execution of this skill's workflow, and reduced reliability of downstream safety or specialization decisions.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger keywords are broad, generic business/product terms such as 'validation', 'prototype', 'saas', and 'startup', which can match many ordinary requests outside this skill’s narrow purpose. This can cause unintended invocation and routing conflicts, leading the agent to apply the wrong workflow, produce irrelevant outputs, or overshadow more appropriate skills.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The default prompt uses a very broad invocation phrase tied to common business, product, and workflow requests, which increases the chance of unintended or overly frequent skill activation. Because implicit invocation is enabled, normal user requests about product ideas, validation, or implementation support could trigger this skill without clear user intent, creating prompt-routing confusion and expanding the attack surface for any downstream risky behavior.

Vague Triggers

High

Confidence: 94% confidence
Finding: The trigger phrases are generic enough to match ordinary product, startup, and workflow requests, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of misrouting user requests, privilege overreach in agent orchestration, and untrusted skill selection based on vague keywords rather than clear user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.