Security audit

Cb Product Market Fit Validator

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a descriptive market-validation planner, but it includes a concrete Amazon review-acquisition tactic that could be non-compliant and should be reviewed before installation.

Install only if you are comfortable editing or ignoring the final usage scenario. Use the framework for planning, interviews, landing pages, and compliant market research, but do not use it to obtain marketplace reviews through incentives, samples, or any tactic that violates Amazon or other platform rules.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (5)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The Chinese usage scenario contradicts the skill's stated 'pure descriptive' boundaries by recommending concrete external actions such as marketplace checking, social/video platform investigation, ad testing, and reviewer/sample tactics. In an agent-skill context, this can normalize or induce browsing, scraping-like behavior, and platform-interaction workflows that exceed declared capabilities and may push downstream agents or users toward policy-violating actions.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The example specifically suggests distributing samples for Amazon reviews, which can be interpreted as incentivized or manipulated review acquisition and directly conflicts with the skill's own prohibition on external actions. This is dangerous because it encourages a concrete marketplace tactic that may violate platform integrity rules and could lead to deceptive or non-compliant behavior.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The examples describe operational tactics that may violate platform policies—especially review acquisition mechanics—without any warning or compliance framing. Even if presented as validation advice, omission of safeguards makes it more likely a user or agent treats the content as endorsed guidance for manipulative growth practices.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest sets "language": "en", which is a natural-language locale constraint. Under the policy, fixed language requirements should either offer user choice/opt-in or be clearly justified as region-specific; neither is present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: This section switches to Chinese for the scenario title, user input, and expected output, but the document does not state that multilingual output is optional or user-selected. That can conflict with language/locale policy expectations because the skill appears to impose a specific language variant in part of the instructions rather than clearly offering user choice.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.