ClawHub
Back to skill

Security audit

Job

Security checks for vulnerabilities and agentic risk

Overview

This is a career-help skill that gives job-search, resume, interview, and offer-negotiation guidance without code execution or hidden access.

Safe to install for job-search assistance, with normal caution around sharing resumes, contact details, salary information, and offer terms. Users should treat the guidance as career advice, not legal, financial, immigration, or mental-health advice, and the publisher should consider narrowing the trigger description to avoid activation in adjacent high-stakes situations.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Vague Triggers

High
Confidence
96% confidence
Finding
The manifest description defines very broad trigger conditions such as "any scenario where someone's professional livelihood is at stake," which can cause the skill to activate far outside a narrowly scoped job-search context. Overbroad activation increases the chance that the system routes sensitive or unrelated user situations into this skill, creating prompt-scope confusion and potentially displacing safer or more appropriate handling.

Static analysis

No suspicious patterns detected.