ClawHub
Back to skill

Security audit

Pinpoint

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Pinpoint read connector using OOMOL's oo CLI, with only minor caution around broad routing wording and first-time CLI setup.

Install this if you want agents to read Pinpoint applications, jobs, and candidates through OOMOL. Review the OOMOL/oo CLI setup and account connection first, and do not approve any future write or destructive Pinpoint action unless the exact payload and effect are clear.

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 skill description says to use this skill for ANY Pinpoint request and instead of calling the API directly, which is an overly broad routing trigger. This can cause the agent to invoke the skill in situations where Pinpoint is only tangentially related, increasing unnecessary exposure to external data access and reducing opportunities for narrower, context-specific validation before tool use.

Static analysis

No suspicious patterns detected.