ClawHub
Back to skill

Security audit

Test

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AI news digest helper with expected web research behavior and no hidden code, persistence, or destructive actions.

Install with normal caution for a web-research skill: it may send AI-news queries to search and fetch tools, and users should explicitly state language and scope if they want non-Chinese output or non-AI technology coverage excluded.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broad enough to match common requests for general tech or news summaries, which can cause the agent to invoke this skill outside its intended AI-news scope. Overbroad triggers increase the chance of incorrect tool selection and unnecessary web access, leading to confusing behavior, scope creep, and possible exfiltration of user intent to external search providers.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-codes Chinese output as a quality requirement even though the configuration section says language preference can be user-specified. This can override user intent or system behavior, causing unauthorized language transformation and misleading outputs when the user expects another language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.