Back to skill

Security audit

test

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only China e-commerce operations advisor with no install scripts, tools, network access, or hidden execution behavior.

Before installing, understand that this skill is specialized for China-market e-commerce and may suggest pricing, campaign, advertising, inventory, and CRM tactics; review any business-impacting recommendations before applying them in real storefronts.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The template and examples prominently prescribe Chinese headings, terminology, and platform-specific Chinese phrasing throughout the skill content. Because the file does not state that the user may choose another language or locale, this can be read as forcing a specific language/locale without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill defines the agent identity exclusively around China e-commerce platforms, campaigns, and market practices, but does not state that this locale specialization is opt-in or limited to region-specific use. Under the policy, locale constraints should either be clearly justified as region-specific or presented with user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation guidance is very broad, telling users to invoke the agent by name or specialty without any scoped trigger, guardrails, or task boundaries. This can cause the skill to activate in situations the user did not clearly intend, increasing the chance of inappropriate delegation or context leakage, though the file contains no overtly malicious behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The identity and experience sections define the skill exclusively around China's e-commerce platforms, RMB budgets, and Chinese campaign events, which imposes a specific regional/locale framing. The file does not state that this localization is optional or explicitly limited to users seeking China-market support, so it can conflict with language/locale policy requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.