ClawHub
Back to skill

Security audit

作业

Security checks for vulnerabilities and agentic risk

Overview

This job-application automation skill is not clearly malicious, but it asks for broad execution authority and can submit applications while giving vague, mismatched, and incomplete operating instructions.

Review this carefully before installing. Use it only for explicit job-search tasks, keep dry-run enabled until you have inspected every target application, require confirmation before submission, and do not provide API keys or personal profile data until the missing implementation and platform behavior are clear.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description explicitly says the skill should be used for broad efficiency, automation, batch processing, and workflow optimization scenarios rather than narrowly constraining it to job-application tasks. In an agent ecosystem, this increases the chance of overbroad auto-invocation and accidental use in unrelated contexts, especially because the skill also advertises exec capability and automated submission behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says '支持中文交互' as a default capability, and no nearby text offers language selection or opt-in for other locales. This can violate language/locale policy when a skill appears to prescribe a specific interaction language without asking the user.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The quick-start tells users to invoke the skill with necessary parameters but does not define specific activation phrases, guardrails, or conditions under which it should or should not run. That ambiguity can cause agents to select this skill too readily for generic automation requests, though the impact is somewhat limited compared with direct hidden execution instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.