Back to skill

Security audit

Cb Platform Selection Guide

Security checks for vulnerabilities and agentic risk

Overview

This skill is a descriptive e-commerce planning guide with no code execution, network access, credentials, or persistence.

This appears safe to install as a planning aid. Users should still verify current marketplace fees, eligibility rules, local laws, tax, and compliance requirements directly because the skill provides guidance, not professional advice or live market data.

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
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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The instruction "Or just describe your product and target market" is not a specific trigger phrase and could match many generic commerce-related conversations. The file does not provide exclusion conditions or boundaries here, so the invocation scope is broader than the earlier, more specific trigger examples.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest sets "language": "en", which indicates a fixed language/locale choice. Under the policy rules, forcing a specific language without user opt-in or a clear region-specific justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

Line L14 states that documentation is "English-first," which is a natural-language locale constraint. Because the text does not offer a language choice or explain a region-specific justification, it may conflict with the policy against forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

These lines present a Chinese-language usage scenario and expected output, but the skill does not explicitly state a language-choice policy or that responses should match the user's requested language. This can create ambiguity about whether the skill may switch or force language/locale behavior without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.