ClawHub
Back to skill

Security audit

Stack Internal

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Stack Internal connector that reads/searches team content through OOMOL, with no hidden persistence or destructive behavior found.

Install this only if you want the agent to query your Stack Internal team content through OOMOL. Be aware that broad Stack Internal requests may cause the agent to use the connector, and only run the CLI install/login/setup steps if you trust OOMOL and intend to connect the account.

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
88% confidence
Finding
The skill description and frontmatter instruct the agent to use this skill for ANY Stack Internal-related request, creating an overly broad routing trigger. That can cause the agent to invoke external tooling for requests that may not require it, increasing the chance of unnecessary data access, privacy exposure, or bypass of more narrowly scoped/native handling.

Static analysis

No suspicious patterns detected.