ClawHub
Back to skill

Security audit

Indeed

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Indeed connector that can read and modify Indeed employer data, with explicit confirmation required for write and destructive actions.

Install this only if you intend to use OOMOL to operate an Indeed employer account. Read-only actions can run directly, but any job posting update or clearing action should be reviewed carefully before approving because it can change Indeed account data.

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
93% confidence
Finding
The trigger text is intentionally broad: 'Use this skill for ANY Indeed request' can cause the agent to invoke this skill for all Indeed-related tasks without narrowing scope to the user's exact intent. In a skill that includes write and destructive actions, overbroad routing increases the chance of unintended state-changing operations being selected or prepared in contexts where a narrower, read-only or direct workflow would be safer.

Static analysis

No suspicious patterns detected.