Back to skill

Security audit

b-comments

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report behavior beyond its stated Bilibili comment-collection purpose, risky security settings, and possible token exposure.

Consider avoiding installation unless you need this skill and can accept the reported risks. Skillspector’s analysis was partial, covering 33.3% of components, and its tool-misuse analysis was degraded, so the evidence is incomplete.

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

Warning
Location
src/config.js
Finding

Public HTTP default exposes account bearer tokens

Content
View full analysis

Impact

An interceptor can capture and replay the token while valid, accessing account-scoped collection data and consuming available collection credits.

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code requests logout, a session-ending operation not described as the skill's purpose. This materially differs from starting and advancing a comment-collection session. The implementation of cli.js is not supplied, so the precise effects of logout cannot be verified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The /b/comments/sessions methods align with the declared stepwise Bilibili workflow. However, the client also exposes equivalent collection workflows for four other platforms and generic /platform/tasks operations, materially broadening its callable capabilities beyond the description. Authentication, request handling, and export infrastructure are supporting implementation details, not independent mismatches. This chunk does not demonstrate automatic invocation of the additional capabilities, nor does it establish server-side pricing, short-link resolution, or CSV formatting.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Configuration storage is a normal supporting implementation detail, and the absence of comment-collection logic in this isolated module is not itself a mismatch. However, automatically importing another skill's credentials and service settings accesses resources beyond the declared Bilibili comment-collection purpose. The code itself acknowledges that conversion and collection are separate services. The default HTTP endpoint is an additional security concern, but this chunk alone does not establish 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.

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
99% confidence
Finding

When invoked, allowInsecureTls disables HTTPS certificate verification process-wide, allowing a network attacker to impersonate the API, capture bearer tokens, and alter responses. This is an optional insecure mode rather than a demonstrated default, but its global scope affects other TLS connections in the process, and warning messages do not restore 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 implements comment-collection capabilities for platforms outside the Bilibili-only skill scope.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest describes collecting Bilibili video comments, but the client also implements session creation, collection steps, and comment retrieval for Xiaohongshu (L134–L159), Douyin (L161–L187), Kuaishou (L189–L215), and Weibo (L245–L272). These are concrete authenticated API operations for unrelated platforms, not implementation requirements of Bilibili collection; their presence does not establish that they are automatically invoked.

Content

No source excerpt is available for this finding.