Back to skill

Security audit

opencli-autofix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed OpenCLI adapter repair workflow that edits only the broken adapter file and asks before posting upstream issues.

Install this only if you are comfortable with an agent modifying OpenCLI adapter source files to repair failing commands. Review local diffs after a repair, especially for adapters under ~/.opencli/clis, and do not use it for failures involving login, CAPTCHA, rate limits, or browser connectivity.

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: opencli-autofix
description: Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
allowed-tools: Bash(opencli:*), Bash(gh:*), Read, Edit, Write
---

# OpenCLI AutoFix — Automatic Adapter Self-Repair
Confidence
83% confidence
Finding
The skill is granted Edit and Write capabilities and instructs the agent to automatically patch adapter code, including files under user-local paths such as ~/.opencli/clis/<site>/. Even though the text tries to constrain edits to adapterSourcePath, that path is derived from trace content and the workflow still enables persistent modification of executable code without an explicit user approval gate before each change, creating risk of unintended or adversarial persistence.

Static analysis

No suspicious patterns detected.