ClawHub
Back to skill

Security audit

Qjzd Nav Cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed routing guide for an existing QJZD Nav CLI and does not itself install code, hide behavior, or request unrelated access.

Install this only if you trust the qjzd-nav CLI binary already on your system. Be careful with --force operations, and treat the shell completion eval commands as executing output from that binary in your shell.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md
- otherwise `$XDG_CONFIG_HOME/qjzd-nav/config.json`
- otherwise `$HOME/.config/qjzd-nav/config.json`

Credentials are stored in the system keyring via `@napi-rs/keyring`.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to run eval "$(qjzd-nav completion ...)", which executes dynamically generated shell code directly in the current shell. Even though shell completion setup is a common pattern, it becomes dangerous if the CLI binary is compromised, replaced in PATH, or emits unexpected output, because arbitrary code would run with the user's privileges.

Content

No source excerpt is available for this finding.