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 access, persistence, code execution, or data handling.

Before installing, be aware that this skill may activate for broad product, startup, validation, or prototype requests. It appears safe to use for planning and checklist work, but the publisher should narrow triggers or disable implicit invocation to reduce accidental routing.

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

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation guidance defines keywords and trigger sentences but does not establish clear activation boundaries or negative examples, so the skill may match loosely related business, prototype, or workflow requests. In a multi-skill agent environment, this increases the chance of overbroad activation and inappropriate routing, which can interfere with safer or more relevant skills and reduce predictability of agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence starts with a very common phrase ('Help me') and then appends a long generic requirement description, which creates an activation surface that is broader than necessary. In agent-routing systems, overly generic triggers can cause the skill to be selected for unrelated user requests, leading to misrouting, unintended instruction application, or prompt-scope confusion.
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 ordinary product/help requests, which increases the chance this skill activates when a user did not explicitly intend to use it. In an agent environment, over-broad activation can misroute benign requests into a specialized workflow, causing unintended actions, confusing outputs, or policy bypass opportunities through prompt shadowing.
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 business, product, and operations requests, which can cause the agent to invoke this skill outside its intended scope. Over-broad routing increases the chance of mis-selection, prompt-surface expansion, and unintended priority over more appropriate or safer domain-specific skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords and example invocations use very generic terms like 'validation', 'prototype', 'saas', and 'startup', which are common across many unrelated requests. This makes accidental or excessive invocation likely, allowing the skill to intercept broad classes of user prompts and potentially override 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 trigger keywords are broad and generic enough to match many normal business or product conversations, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of unintended instruction injection into unrelated workflows, user confusion, and inappropriate handling of requests that should be routed elsewhere.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The default prompt uses very broad, everyday phrasing around founders, builders, product ideas, validation, prototypes, and implementation support, which overlaps heavily with common user speech. Because this language is generic, routine conversation may be interpreted as an invocation cue, causing accidental activation of the skill and allowing its instructions to shape outputs in contexts the user did not clearly request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill enables implicit invocation while providing only a broad business/product-oriented description, which makes it easier for normal user requests about products, validation, workflows, or planning to trigger the skill unintentionally. This expands the attack surface for prompt injection, unexpected tool activation, or unwanted influence over conversations because the invocation boundary is not narrowly constrained.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The usage signals section defines ambiguous activation criteria using generic keywords and truncated trigger sentences, without clear boundaries for when the skill should or should not run. This makes accidental invocation more likely and can let the skill intercept common business or planning requests that were not meant for it, reducing routing integrity.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentence is extremely broad and can match ordinary requests about product ideas, validation, or workflows, which increases the chance the skill activates outside its intended scope. Overbroad activation can cause the agent to route unrelated conversations into this skill, creating prompt-surface expansion and unintended influence over user interactions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file explicitly labels this document as the Chinese-language user guide ("README.zh-CN.md" / "中文版用户说明") without any indication that users may choose another language or locale. Under the policy rule, fixed language presentation without opt-in can be a locale-policy issue unless clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: This localized zh-CN skill presents its activation interface primarily in English keywords and example trigger sentences, but does not state that users may choose their preferred language. That can impose a language expectation without clear opt-in or alternative localized triggers.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.