ClawHub
Back to skill

Security audit

hillstreet-integrations-mobile

Security checks for vulnerabilities and agentic risk

Overview

The skill receives a benign verdict with high confidence: scanners found one low-probability concern about autonomous decision-making, while all four inspected components were covered and no AIG findings were reported.

The verdict is benign, not a guarantee of zero risk. The scan reports complete coverage of the four components and no failed or partial analysis; it also records the low-probability EA2 concern. Consider whether that concern matters for how you plan to use the skill before installing.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/mobile-use.md (reported line 5)May include surrounding context.

md
Open the already connected Open-Connect app in ChatGPT and choose **Try in chat**. Include OpenConnect Integrations Skills for the instructions. A skill supplies the workflow; the selected app supplies the remote tools. Keep the existing app and account connection.

Start with: “Use Open-Connect and OpenConnect Integrations Skills to show my connection readiness and available tools.” Discover the current schemas and perform bounded reads. Do not ask the user to install a terminal, Python, Docker, or a desktop executor on Android.

| Request | Execution path |
| --- | --- |