Security audit

Product Validation Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only product validation planning skill with no executable code, persistence, credential access, or hidden data handling.

Installers should expect this skill to influence product validation and startup planning conversations. Review the broad trigger terms if you use many skills, because it may activate for general business or SaaS requests where a more specific skill would fit better.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 skill description is broadly scoped to common startup and product-help requests such as business operations, product ideas, validation, prototypes, and implementation support. Because these categories are common and loosely bounded, the skill can be invoked in many situations beyond its intended niche, increasing the chance of inappropriate routing, prompt shadowing of more suitable skills, or accidental capture of unrelated user tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger examples are very broad and resemble ordinary user requests, which can cause the skill to activate in situations beyond the author's intended scope. Overbroad activation increases the chance of unintended instruction injection into unrelated conversations and may steer the agent into business-validation workflows when the user did not explicitly request this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are very broad and can activate on generic business, validation, prototype, or startup-related requests without clear boundaries. This increases the chance the skill is invoked inappropriately, causing prompt-routing confusion, unintended scope expansion, or use in contexts the skill was not designed to handle.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords and example invocations use generic terms like 'validation', 'prototype', 'saas', and 'startup', which are ambiguous and likely to match many ordinary user requests. This makes over-triggering likely, causing the agent to select this skill when another skill or a general response would be more appropriate, which can degrade reliability and create unsafe behavior composition when skills compete.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest description says to use the skill whenever users ask about broad categories such as business-and-operations, product ideas, validation, prototypes, or SaaS, which creates an activation surface far wider than the specific capability described. This can cause the assistant to route loosely related requests into this skill, potentially overriding better-suited behavior and exposing users to irrelevant or biased planning outputs.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords and example invocations are broad enough to match many ordinary startup, product, or SaaS conversations, which can cause the skill to activate outside a narrowly intended scope. Over-broad activation increases the chance of inappropriate context injection, misleading workflow steering, or unintended handling of user requests that did not explicitly ask for this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt invokes the skill with a very broad phrase tied to common product, business, validation, prototype, and workflow requests, which can cause the agent to route unrelated or weakly related user queries into this skill without clear consent or boundaries. Because implicit invocation is also enabled, the broad trigger surface increases the chance of accidental activation, prompt collision with other skills, and unintended exposure of this skill's instructions in contexts where it is not the best match.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentence begins with a very broad phrase ('Help me') and then appends a long requirement description, making activation criteria overly permissive and likely to match ordinary user requests that were not intended to invoke this skill. Overbroad triggers can cause inappropriate routing, unexpected execution of the skill, and interference with more relevant or safer skills in a multi-skill agent environment.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: These trigger sentences are ambiguous because they embed a generic requirement statement rather than concrete user intents, so many unrelated requests could partially match them while legitimate requests may still be unclear. In practice this increases false activations, weakens routing precision, and may cause the agent to apply business-planning guidance in contexts where the user asked for something else.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The file describes separate English and Chinese instruction and guide files, but it does not state how the user's preferred language is selected or that the user can choose. This can create an implicit language/locale constraint without documented opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: This is a zh-CN README, but key usage content including the workflow description and trigger phrases is presented in English only. That imposes a language choice on users of the localized document without explicit opt-in or an offered alternative.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.