ClawHub
Back to skill

Security audit

Lever

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a normal Lever integration, with one routing-scope caution but no evidence of hidden, destructive, or deceptive behavior.

Install only if you intend your agent to handle Lever tasks through this skill. For candidate, job, offer, or pipeline changes, ask the agent to preview the exact action and get your confirmation before making updates.

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

Medium
Confidence
91% confidence
Finding
The trigger language says to use this skill for ANY Lever request and instead of calling the API directly, which can cause the agent to invoke the skill too broadly without first considering whether the request is appropriate, read-only, or requires stronger confirmation. In a skill that includes write actions, broad routing increases the chance of unintended state-changing operations or overuse of an external integration when a narrower tool selection policy would be safer.

Static analysis

No suspicious patterns detected.