Security audit

Product Validation Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only product validation planning skill with broad trigger wording but no hidden code, data access, persistence, or privileged behavior.

Installers should be aware that this skill may trigger more often than intended for broad product or business requests. Review the output for fit, but the package does not appear to perform hidden actions or access sensitive data.

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 (8)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description activates on very broad terms like business-and-operations, product idea, prototype, and practical workflow, which are common across many unrelated user requests. This can cause the skill to be invoked outside its intended niche, increasing the chance it overrides more appropriate skills or handles requests with assumptions and workflows that do not fit the user's actual task.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger sentences are broad, repetitive, and loosely scoped, which can cause the skill to activate for generic business, product, or workflow requests beyond its intended validation-planning use case. Overbroad activation increases the chance of incorrect routing, prompt interference with other skills, and unintended handling of user requests in contexts where this skill is not appropriate.
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 generic terms like product idea, validation, prototype, and startup, plus broad natural-language examples that could match many unrelated user requests. This increases the likelihood of unintended skill invocation, which can route conversations into the wrong workflow, cause prompt-scope confusion, and make downstream behavior less predictable.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger list uses generic keywords such as validation, prototype, saas, and startup without contextual qualifiers or negative examples. In routing systems, this makes accidental activation likely for many benign or unrelated requests, which can degrade agent behavior and potentially expose users to irrelevant guidance or tool usage paths not intended for the request.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: 该技能文件整体以中文编写，且未说明用户可以选择其他语言或根据用户偏好切换输出语言。按照语言/区域政策，若技能默认强制特定语言而没有用户选择或明确 justification，可能构成自然语言策略违规。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords are broad and common terms such as 'validation', 'prototype', 'saas', and 'startup', which can cause the skill to activate for many unrelated requests. This increases the chance of unintended routing, confusing user experience, and inappropriate application of the skill's workflow to contexts where it does not fit.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt embeds a broad activation phrase and a generic instruction to use the skill for a wide set of business and product tasks, without meaningful constraints on when invocation is appropriate. Combined with allow_implicit_invocation: true, this increases the chance the agent will trigger the skill in contexts the user did not clearly intend, causing prompt-scope expansion, unintended data sharing to the skill, or overbroad autonomous behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is overly broad and can cause the skill to activate on common product or business discussions that do not actually require this specific workflow. Over-broad routing increases the chance of unintended invocation, which can override user intent, create confused-deputy behavior between skills, or expose users to irrelevant planning guidance in contexts where another tool should respond.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.