ClawHub
Back to skill

Security audit

新闻

Security checks for vulnerabilities and agentic risk

Overview

This news-summary skill is not clearly malicious, but it requests shell execution without a clear news-related need and has inconsistent documentation.

Review before installing. The skill appears intended to summarize news, but it asks for shell execution even though the documented workflow does not need it. Install only if you are comfortable with that permission, and prefer a version that removes exec or clearly limits exactly which commands may run.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill declares the exec tool even though its documented purpose is news aggregation and summarization, which should typically require only read/search/network capabilities. Granting shell execution to a content-processing skill unnecessarily expands its privilege boundary and creates a path for command execution if downstream prompts, templates, or fetched content are used unsafely.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The paid capability matrix states 定时监控与变化推送 is supported, indicating scheduled monitoring and push notifications. Later, the FAQ explicitly says 不提供实时推送功能，需主动发起查询, which directly contradicts that earlier claim about push behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Overly broad invocation guidance can cause the agent to trigger this skill in contexts beyond straightforward news aggregation, increasing the chance that untrusted user content or unrelated tasks are routed into a skill with unnecessary exec capability. In this file, that ambiguity is more dangerous because the skill already requests elevated functionality inconsistent with its stated purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.