ClawHub
Back to skill

Security audit

Social Commerce Content Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese-language social commerce content planner with no network access, dependencies, persistence, credential use, or hidden high-impact behavior.

Install this if you want Chinese social-commerce planning templates. Review generated marketing claims and dates yourself, especially for regulated products or platform-specific compliance, because the skill uses static guidance and no real-time APIs.

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
  • 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
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger section includes broad phrases such as general requests for help with e-commerce content, which can cause the skill to activate on ordinary user queries without clear intent to invoke this specific workflow. Over-broad activation increases the risk of prompt/skill hijacking at the orchestration layer, unexpected execution, and accidental generation of marketing content in contexts where the user did not explicitly request it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code returns user-facing content, labels, request aliases, and test output exclusively in Chinese, which effectively forces a specific language/locale. The file does not provide any opt-in, fallback, or documented justification for restricting output to Chinese only.

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 specifies "language": "zh-CN", which indicates the skill is constrained to Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified or optional, and no such justification or choice appears in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code's natural-language content, test inputs, assertions, and output messages are consistently fixed to Chinese, such as the title, platform/category inputs, and printed status strings. Under the policy, forcing a specific language without user opt-in can be a locale-policy violation, and this file does not indicate that the skill is intentionally region-specific or offers an alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The target users are described only in Chinese and the examples and workflow are entirely oriented to Chinese social-commerce platforms, with no indication that users may choose another language or locale. This may constitute a language/locale policy issue if the organization expects skills not to force a specific language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.