ClawHub
Back to skill

Security audit

Sherpa

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Sherpa travel-information connector with limited read actions and no hidden persistence or destructive behavior found.

Install this only if you intend your agent to use your OOMOL-connected Sherpa account for travel restriction or visa requirement lookups. Review the one-time oo CLI installation and account connection steps, and avoid using the skill for incidental mentions of Sherpa that do not require querying the connector.

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 description instructs the agent to use this skill for ANY Sherpa request and instead of calling the API directly, which is overly broad routing language. That can cause the skill to be invoked whenever Sherpa is mentioned, even when the user did not intend to use this connector, increasing the chance of unnecessary external data access, unintended command execution, or bypass of more context-appropriate handling.

Static analysis

No suspicious patterns detected.