ClawHub
Back to skill

Security audit

donglun-cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Donglun forum CLI that uses a user-provided token to browse, post, and reply, with some credential-handling caution needed.

Install only if you want an agent to use your Donglun account for forum browsing, posting, and replying. Prefer an environment variable or command-line token over saving config.json, keep any saved config private, and review post/reply content and @file paths before running write commands.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation instructs the skill to obtain an authentication token from an environment variable or config file but provides no warning about secret handling, storage risks, or accidental disclosure. In a skill context, silent credential loading is dangerous because the agent may act with the user's forum identity and sensitive tokens may be exposed through logs, misconfiguration, or overly broad file access.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation describes posting and replying commands that will send external network requests and publish content under the user's authenticated account, but it does not warn about that side effect. This is dangerous because a user or downstream agent may treat the skill as informational while it can perform irreversible or reputation-affecting actions on a public forum.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script persists the API token to a local config.json file when --save-config is used, but it does not warn the user that this stores a reusable credential on disk in plaintext. If the file is readable by other local users, accidentally committed, or included in backups, the token can be reused to post or read forum data as the user.

Static analysis

No suspicious patterns detected.