ClawHub
Back to skill

Security audit

酷安社区搜索

Security checks for vulnerabilities and agentic risk

Overview

This Coolapk helper is coherent, but it needs review because it asks users to pass an account cookie on the command line and exposes account-changing actions without clear confirmation safeguards.

Review before installing. Use it only if you trust the coolapk-mcp package and intend to let an agent operate your Coolapk account. Avoid putting long-lived cookies directly in shell commands, prefer an isolated Python environment, and require explicit approval before any reply, like, follow, or unfollow action.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README states that a Python package will be automatically installed via pip on first use, but it does not clearly warn users that invoking the skill may download and execute third-party code or modify the local environment. In an agent/CLI context, silent dependency installation increases supply-chain and unexpected code-execution risk because users may assume the skill is read-only search functionality.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README advertises login-required actions such as liking, replying, and following, plus notification access, without warning that using the skill can perform account-affecting operations and expose private account data. In an AI-agent setting, this is dangerous because a user may authorize or invoke the skill expecting passive retrieval, while the tool can trigger irreversible or privacy-sensitive actions under their account.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs users to pass authentication cookies directly on the command line, which can expose sensitive session material through shell history, process listings, terminal logging, or audit systems. Because these cookies appear sufficient to authenticate the user, disclosure could let another local user or monitoring system hijack the account session.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill exposes account-modifying commands such as like, unlike, reply, follow, and unfollow without clearly warning that they perform external, state-changing actions on the user's Coolapk account. In an agent/tooling context, this increases the risk of unintended social actions, spammy behavior, or account misuse if the commands are invoked automatically or without explicit user confirmation.

Static analysis

No suspicious patterns detected.