ClawHub
Back to skill

Security audit

opencli-usage

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent OpenCLI orientation skill, but users should be deliberate before running its install, plugin, or live-session browser commands.

Install only from sources you trust, review any OpenCLI plugin or external CLI before installing or updating it, and be aware that COOKIE, HEADER, INTERCEPT, UI, and Electron workflows can use your already logged-in browser or app session.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description is written as a broad catch-all entry point for 'any OpenCLI session' and generic questions like 'what can opencli do?', which can cause over-triggering in many routine contexts. Overbroad activation increases the chance an agent loads this skill unnecessarily and follows risky operational guidance, including install, plugin, and passthrough workflows, when a narrower skill would be safer.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs installation of plugins from git and auto-installation/registration of external CLIs without any safety warning, trust boundary, or provenance verification guidance. In an agent setting, this can normalize executing untrusted code or package-manager installs from remote sources, creating a real supply-chain compromise path.

Session Persistence

Medium
Category
Rogue Agent
Content
opencli plugin list [-f json]              # see installed
opencli plugin update [name] | --all       # keep current
opencli plugin uninstall <name>
opencli plugin create <name>               # scaffold a new plugin
```

## External CLI passthrough
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium
Category
Rogue Agent
Content
opencli plugin list [-f json]              # see installed
opencli plugin update [name] | --all       # keep current
opencli plugin uninstall <name>
opencli plugin create <name>               # scaffold a new plugin
```

## External CLI passthrough
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.