ClawHub
Back to skill

Security audit

CyberInterviewer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent text-only interview-prep skill that reads user-provided resumes and repositories for its stated purpose, with no bundled executable code or persistence.

Install only if you are comfortable letting the agent read the resume and repository paths you provide and perform live web searches for interview research. Avoid pointing it at unrelated private repositories or sensitive files outside the interview-prep scope.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
- Do not depend on executable helpers or local runtime files.
- If `references/` files are available, use them as supporting guidance.
- If they are unavailable, continue using only the workflow and rules in this document.
- Never say you cannot proceed only because a helper file was not loaded.

The core job of this skill is to turn a resume plus one or more repositories into a realistic, high-pressure technical interview grounded in code evidence instead of generic interview advice.
Confidence
85% confidence
Finding
Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Ae1

High
Category
analysis-evasion
Content
- `SKILL.md`: the main operating manual
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
Lines L012-L014 and L032 state that the skill is text-only and should not depend on executable helpers or local runtime files. However, L577-L583 explicitly permit reading or executing other files including `src/index.py`, which contradicts the earlier operating constraints and creates ambiguity about whether code execution is part of the skill.

Static analysis

No suspicious patterns detected.