Security audit

Product Validation Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only product validation planner with broad auto-invocation wording, but no hidden code, credential use, persistence, or destructive behavior.

Installers should be aware that the skill may be selected automatically for broad product or business-planning requests. It is otherwise a low-risk planning aid; review outputs for fit before acting on business decisions.

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 (13)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger phrases are generic help-seeking sentences that overlap with normal user requests about workflows, validation, and product ideas. This can cause the skill to activate unintentionally, leading to prompt-routing errors, unexpected handling of user input, and reduced control over which skill is invoked. In this business-planning context the issue is operational rather than directly code-executing, but broad invocation still increases the attack surface for misrouting and prompt confusion.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The activation examples are ambiguous and do not define what should or should not invoke the skill, making accidental or excessive triggering more likely. In an agent ecosystem, this can misroute user requests, expose internal skill behavior in the wrong context, or let a loosely matching request invoke capabilities the user did not clearly intend to use.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrase is broad enough to match ordinary user requests about workflows or validation, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of unintended routing, prompt/context injection into unrelated conversations, or bypass of more appropriate skills through ambiguous matching.
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 activate on many generic business, product, or implementation requests, which can cause the agent to invoke this skill outside its intended scope. Over-broad routing is dangerous because it can override a more appropriate skill, produce irrelevant guidance, and increase exposure to prompt-surface abuse by making activation easier from ordinary user phrasing.
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 phrases are ambiguous and high-frequency, especially terms like 'prototype,' 'saas,' 'validation,' and 'startup,' which appear in many unrelated requests. This makes unintended invocation likely and weakens routing precision, allowing the skill to capture requests that should be handled by other, more specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The activation description covers a very wide range of requests across business operations, product ideas, validation, prototypes, SaaS, workflows, analysis, and implementation support. This ambiguity can make the skill match too many user requests, leading to incorrect skill selection and unreliable downstream behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords are broad generic business terms like "validation," "prototype," and "startup," which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance of inappropriate routing, causing the agent to apply this workflow when the user did not request it and potentially crowding out more suitable skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt uses a very broad trigger phrase covering multiple generic business/product tasks, which can cause the skill to be invoked in contexts beyond its intended scope. This increases the chance of prompt-surface expansion, unintended routing, and the skill influencing requests where users did not explicitly ask for it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Implicit invocation is enabled even though the skill description and prompt scope are broad, allowing the agent to auto-select this skill for loosely related requests. In practice, this can lead to over-activation, unreviewed prompt injection exposure through the skill path, and unintended handling of user workflows without clear user consent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence begins with a very broad everyday phrase ('Help me') and then appends a long requirement description, making activation scope unclear and increasing the chance the skill is invoked for loosely related requests. In an agent environment, overly broad triggers can cause unintended routing, suppress more appropriate skills, or expose users to irrelevant automation without explicit intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The sentence 'I need a practical workflow for ...' is still too generic because 'practical workflow' applies to many domains and does not clearly delimit when this skill should activate. That ambiguity can lead to over-triggering on general planning or operations requests, causing incorrect tool selection and reducing trust in the agent's routing behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 74% confidence
Finding: This file is a Chinese-localized README, but there is no visible statement that language should be selected based on user preference or that Chinese output is optional. If this localized skill documentation is used as an instruction source, it may imply a fixed locale without explicit user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This localized zh-CN skill presents trigger keywords and example invocations primarily in English, which can effectively impose a language expectation without explicitly offering the user a language or locale choice. That may conflict with language/locale policy expectations for user-facing skill behavior.
Content: No source excerpt is available for this finding.