ClawHub
Back to skill

Security audit

Interview Simulator

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only mock interview skill with no code execution, persistence, or hidden access, though users should be careful when sharing resume details.

Before using the resume-based flow, remove unnecessary personal information such as phone numbers, addresses, identifiers, and confidential employer details. Consider using a clear phrase like 'mock interview for...' when you want the skill active.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README encourages users to paste or upload resumes for targeted interviewing but provides no warning that resumes commonly contain sensitive personal data such as phone numbers, addresses, employment history, and other identifiers. This creates a privacy risk because users may disclose unnecessary personal information to an LLM or third-party platform without understanding retention, logging, or sharing implications.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The invocation examples include broad, natural phrases such as 'Help me prepare' that could unintentionally activate the interview behavior when a user is asking for general assistance rather than explicitly opting into the skill. In a prompt-based skill loaded into system instructions, ambiguous triggers increase the risk of mode confusion and unexpected behavior, especially if the host platform routes ordinary user messages through the skill.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · README.md (reported line 11)May include surrounding context.

md
## Identity

You are a **professional interview simulator**. You can role-play as an interviewer for **any profession or role**, including but not limited to:

- **Engineering**: Frontend Engineer, Backend Engineer, Mobile/Client Engineer, Full-stack Engineer, DevOps/SRE, Data Engineer, Machine Learning Engineer, Embedded Engineer, QA/Test Engineer
- **Product & Design**: Product Manager, UI/UX Designer, Technical Writer

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 5)May include surrounding context.

md
## Identity

You are a **professional interview simulator**. You can role-play as an interviewer for **any profession or role**, including but not limited to:

- **Engineering**: Frontend Engineer, Backend Engineer, Mobile/Client Engineer, Full-stack Engineer, DevOps/SRE, Data Engineer, Machine Learning Engineer, Embedded Engineer, QA/Test Engineer
- **Product & Design**: Product Manager, UI/UX Designer, Technical Writer

Static analysis

No suspicious patterns detected.