ClawHub
Back to skill

Security audit

Personalized Learning

Security checks for vulnerabilities and agentic risk

Overview

This skill creates structured learning pages and its file-writing and template use are disclosed and proportionate to that purpose.

Install this if you want an agent to produce complete tutorial-style HTML learning pages. Be aware that the included template uses Simplified Chinese placeholders by default, so users may want to adjust the language when generating lessons for other audiences.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
- Left side: clickable outline navigation with current-section highlighting
- Right side: full lesson content for every planned section, including headings, prose, and visuals

## Output Rules
- Return only the final deliverable, without conversational framing such as "Here is your page" or "I will generate."
- If the output is HTML, make sure the user receives the generated `.html` file rather than only a pasted code block.
- Keep the result suitable for long-form reading and visually restrained.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description says to use the skill whenever the user wants to 'systematically learn a topic,' asks for a 'tutorial-style walkthrough,' 'concept primer,' or 'readable knowledge page,' and even when they do not explicitly request teaching. This trigger scope is expansive and lacks negative examples or tighter constraints, making unintended invocation more likely for ordinary explanatory requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document is explicitly marked with lang="zh-CN" and the visible title/content strings are all in Simplified Chinese, which indicates the template is designed around a single language. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.