Security audit

Product Validation Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only product validation planning skill with somewhat broad activation wording but no evidence of code execution, data access, persistence, or hidden behavior.

Before installing, be aware that the skill may activate for broad product or startup discussions because implicit invocation is enabled and the trigger terms are generic. It appears safe as a planning/documentation helper, but users who want precise routing should narrow the trigger phrases or invoke it explicitly.

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

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentence begins with a very generic phrase ('Help me') and then appends a long requirement statement, which makes activation conditions unclear and overly broad. In agent routing systems, vague triggers can cause the skill to activate for unrelated business or product conversations, increasing the chance of unintended instruction injection into contexts where this skill was not explicitly requested.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The invocation examples rely on pasting a long natural-language requirement description instead of using bounded, deterministic trigger phrases. This ambiguity can lead to accidental matching on loosely related requests, causing inappropriate skill selection and expanding the attack surface for prompt-routing abuse or unintended execution paths.
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 broad and map to common requests like product ideas, validation, and practical workflows, which can cause the skill to activate in many ordinary conversations beyond clearly scoped user intent. Over-broad activation increases the chance of inappropriate routing, prompt overshadowing, or accidental use of this skill when another tool or a neutral response would be safer and more relevant.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description is broad enough to match many ordinary business, product, and operations requests, which can cause the agent to invoke this skill outside its intended scope. Over-broad activation increases the chance of unintended routing, prompt-surface expansion, and inappropriate reliance on the skill's instructions in unrelated contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords are highly generic terms commonly used in normal conversation, making accidental or excessive skill activation likely. This weakens routing integrity and can let the skill capture prompts it should not handle, especially in multi-skill environments where precise dispatch boundaries matter.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill is written entirely in Chinese and does not state whether users may interact in other languages or choose their preferred language. This can cause misunderstanding, incorrect outputs, or unsafe assumptions if the skill is invoked for users expecting another language, but it is primarily a usability and routing weakness rather than a severe security flaw.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description and frontmatter scope are broad enough that ordinary product or business discussions could trigger this skill unintentionally. Over-broad activation can cause inappropriate routing, irrelevant guidance, or concealment of more suitable skills, though it does not directly enable code execution or data exfiltration.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The keyword trigger list is overly generic and lacks qualifiers or exclusions, so common terms like product idea, validation, prototype, or startup may match many unrelated conversations. This increases accidental invocation risk and can degrade system behavior by routing users into the wrong workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The default prompt contains broad, everyday trigger terms like 'help me' and generic business/product language, which can cause the skill to be invoked in situations far beyond its intended scope. Because implicit invocation is enabled, this increases the chance of accidental routing, prompt hijacking via ambiguous matching, or untrusted delegation into a skill that may influence user workflows unexpectedly.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are broad enough to match many ordinary product, startup, or workflow requests, which can cause the skill to activate outside its intended scope. Over-broad activation is risky because it can override more appropriate skills, create prompt-routing confusion, and increase the chance that users receive mismatched guidance without realizing a specialized tool was not selected.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The file references separate English and Simplified Chinese documentation variants, but this README itself is a zh-CN localized file and does not indicate that users may choose their preferred language. This can be interpreted as imposing a specific locale presentation without explicit user opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.