Back to skill

Security audit

ks-comments

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report exposed account tokens, insecure TLS support, and capabilities beyond its stated Kuaishou comment-collection purpose.

Consider the suspicious verdict and reported token exposure and broader-than-described capabilities before installing. Skillspector inspected only 2 of 6 components, with partial analysis of 4 others, so the evidence is incomplete and does not establish the full behavior.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
src/config.js
Finding

Default HTTP transport exposes account bearer tokens

Content
View full analysis

Impact

An interceptor can capture and replay the bearer token to access account APIs, retrieve collected data, and invoke credit-consuming collection steps as the victim.

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The /ks/comments/sessions methods align with the declared purpose. However, the module also exposes parallel operations under /comments, /dy/comments, /b/comments, and /wb/comments, as well as generic /platform/tasks operations. These are additional callable capabilities outside the Kuaishou-only description. Authentication, HTTP handling, timeouts, and export helpers are supporting implementation details, not independent mismatches. This chunk does not demonstrate that the additional methods are invoked, nor does it establish server-side pricing, URL resolution, or CSV formatting.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

声明描述的是快手评论采集、分页会话和 CSV 导出,而提供的代码仅调用 logout 子命令。退出认证会话并非所声明的采集流程,属于未声明且目的不同的操作。由于未提供 cli.js,无法确认该命令实际修改了哪些认证状态或资源。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

Ordinary configuration and token management are supporting implementation details and do not themselves constitute a mismatch. The material discrepancy is automatic cross-tool credential and connection-setting migration: resolving configuration can access another tool's credential store without an explicit migration request. That resource access is not represented in the Kuaishou comment-collection description. The default HTTP URL is a security concern, but this chunk alone does not demonstrate credential transmission or exfiltration.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Mandatory verbatim Chinese registration guidance imposes a language without user opt-in.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The skill requires the agent to send the registration guidance verbatim, and the prescribed guidance is in Chinese. This forces Chinese output regardless of the user's language, without offering a language choice or documenting a justification for the restriction.

Content

No source excerpt is available for this finding.

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
99% confidence
Finding

Calling allowInsecureTls disables certificate verification process-wide, allowing an active network attacker to impersonate HTTPS services and intercept bearer tokens or alter API responses. The function is exported rather than enabled by default in this file, so exploitation requires its invocation or equivalent configuration; stderr warnings do not restore transport authentication.

Content

Scanner excerpt · src/client.js (reported line 17)May include surrounding context.

js
/** 忽略 HTTPS 证书校验 (服务端自签/域名不匹配证书时由 insecure 配置开启)。进程级。 */
function allowInsecureTls() {
  process.env.NODE_TLS_REJECT_UNAUTHORIZED = '0';
}

/** 业务错误: code 为后端错误码 (1001/1002/3001/...) */

The exported client includes comment-collection capabilities for platforms outside the declared Kuaishou scope.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The manifest describes only Kuaishou comment collection, but the client also implements session creation, collection steps, and comment retrieval for Xiaohongshu (L134–L159), Douyin (L161–L187), Bilibili (L217–L243), and Weibo (L245–L272). These are operational API methods on the exported ApiClient, not merely documentation, and provide unrelated platform capabilities; this file does not show that they are automatically invoked.

Content

No source excerpt is available for this finding.