Security audit

Product Validation Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only product validation planning skill, with the main caveat that its broad triggers may activate it for general business or startup requests.

Installers should expect a product-validation planning assistant that may be invoked broadly for startup or product discussions. Review its outputs as business guidance, especially because the cited demand evidence is noisy, but the artifacts do not show unsafe execution, data access, persistence, or deception.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is so broad and generic that it can match ordinary user requests about product ideas, workflows, or implementation support without strong evidence that this specific skill is the right tool. Overbroad activation increases the chance of unintended invocation, which can route users into irrelevant or lower-quality behavior and, in multi-skill environments, can be abused to hijack requests that should go to a more appropriate skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger phrases are generic enough to match many ordinary product or business-help requests, which can cause the skill to activate outside its intended scope. Over-broad invocation increases the chance of prompt-routing mistakes, unnecessary exposure of internal skill instructions, or the model prioritizing this workflow when a more appropriate skill should handle the request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are broad, generic help-seeking prompts that can match many ordinary user requests unrelated to this specific skill. In an agent routing system, this can cause unintended auto-invocation, pulling users into a business-planning workflow when they did not explicitly request it and potentially overshadowing more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description is broad enough to match many ordinary product, startup, and operations requests, increasing the chance the agent invokes this skill outside its intended niche. Over-broad activation can cause inappropriate routing, overshadow more specific skills, and lead to users receiving workflow-driven business guidance when they asked for something narrower or different.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger section relies on vague keywords such as 'prototype', 'saas', and 'startup' without boundary conditions, so the skill may activate for a wide range of unrelated or only loosely related requests. In an agent environment, this can create prompt-routing abuse or persistent misselection, reducing reliability and potentially causing the wrong skill to shape downstream outputs.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description uses broad categories like business-and-operations, product idea, validation, prototype, and saas without clear boundaries or exclusion criteria. This can cause the skill to activate during ordinary product discussions and steer the agent into an unintended workflow, increasing the chance of irrelevant guidance, prompt collisions, or bypass of more appropriate specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The keyword list is overly generic and consists of common terms frequently appearing in normal conversations, which makes accidental triggering likely. In an agent system, broad triggers can hijack routing, causing the wrong skill to run and potentially suppress safer or more relevant behaviors.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt uses a very broad invocation phrase tied to common business and product-planning requests, which increases the chance of unintended or implicit activation outside a narrowly scoped user intent. Because implicit invocation is also enabled, the agent may be selected in contexts where its guidance is not expected, creating prompt-routing risk and unnecessary exposure of the skill's instructions or behaviors.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The invocation guidance lists broad keywords like 'business-and-operations', 'prototype', 'saas', and 'startup' and pairs them with vague trigger sentences, but it does not define sufficient constraints for when the skill should or should not activate. This creates ambiguous routing behavior, making accidental selection more likely and reducing the reliability and safety of the skill-selection layer.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The file presents itself as a Chinese-language user guide variant ('README.zh-CN.md'), which indicates a locale-specific document, but there is no explicit user choice or opt-in language guidance within the content. Under the policy, locale constraints should either be optional for the user or clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: 该技能文件为 zh-CN 版本，正文与触发说明均默认以中文面向用户，但未声明用户可选择其他语言，也未说明这是仅面向特定区域/语言环境的专用技能。按自然语言策略，这种默认固定语言而无选择提示可能构成语言/地区策略问题。
Content: No source excerpt is available for this finding.