Security audit

Product Validation Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only product validation planning skill with broad activation wording but no hidden execution, data access, persistence, or credential handling.

Safe to install for product-validation planning. Be aware that its trigger terms are broad, so it may appear for general startup, SaaS, prototype, or validation requests where a narrower skill might be 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

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 (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence begins with a very broad everyday phrase ('Help me') and then appends the requirement text, making activation possible in many benign user conversations that are only loosely related to the skill. Over-broad trigger patterns increase the chance of unintended routing or invocation, which can cause the agent to apply this skill in the wrong context and produce misleading business guidance or bypass more appropriate specialized handling.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad enough to match common product and workflow requests, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of unsolicited instruction injection into unrelated conversations and can steer users into this skill when they did not explicitly opt into it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad and map to common user intents like 'practical workflow' and generic startup/product-help requests, which can cause the skill to activate in situations beyond its narrowly intended scope. Over-broad activation increases the chance of unintended instruction injection into unrelated conversations and can interfere with more appropriate skills or baseline behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is broad enough to match many ordinary business, startup, and product-planning requests, which increases the chance of over-invocation. An overly generic activation scope can cause the agent to route unrelated prompts into this skill, producing unintended behavior, reducing least-privilege prompt routing, and potentially overshadowing more appropriate skills or safeguards.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords and example phrases are highly generic terms like 'validation,' 'prototype,' 'saas,' and 'startup,' which are common across many unrelated requests. This makes accidental triggering likely and weakens reliable skill selection, especially in multi-skill environments where broad keyword matches can hijack normal routing and bypass more specialized handling.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description embeds very broad business/product terms as activation context without clear narrowing conditions, so the skill may be selected for many unrelated startup or planning requests. Over-broad routing can cause unintended invocation, increasing the chance that users receive irrelevant guidance or that this skill overrides a more appropriate specialized skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list includes generic terms like business-and-operations, product idea, validation, prototype, saas, and startup, all of which appear in many unrelated requests. This creates a real misrouting risk where the agent may invoke this skill too often, reducing reliability and potentially suppressing safer or more relevant domain-specific behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt uses a very broad natural-language invocation phrase tied to common business, product, and workflow requests, which increases the chance of unintended or implicit activation. Because the policy also enables implicit invocation, ordinary user requests about product ideas or validation may trigger the skill without clear user intent, expanding the attack surface and making prompt-routing mistakes more likely.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The phrase 'I need a practical workflow for ...' is still a broad activation pattern because it can match many routine planning requests without clearly constraining the subject to product validation. In a multi-skill environment, this can lead to accidental triggering, incorrect tool selection, and over-collection or generation of business-planning artifacts for requests that did not intend to use this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The file explicitly defines English and Chinese documentation variants, but does not state how the skill chooses between languages or whether the user can opt in to a preferred locale. This can create a locale-policy ambiguity if the skill defaults to one language without user choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This file is a Chinese-language user-facing README and labels itself as the Chinese version, but nowhere in the content does it offer a user language choice or explain a required locale constraint. For a user-facing skill description, this can be interpreted as a language/locale policy issue when no opt-in or justification is stated in the file itself.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: 该文件整体以 zh-CN 形式提供内容，但未见任何说明表明语言是用户自选、可切换或因合规/区域需求而限定。按自然语言策略要求，若技能对语言或区域有约束，应提供用户选择或明确、合理的限定说明。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.