ClawHub
Back to skill

Security audit

News Aggregator Skill

Security checks for vulnerabilities and agentic risk

Overview

This news skill is not clearly malicious, but it needs review because it references missing executable files and always writes saved reports without a clear opt-out.

Install only if you are comfortable with a news skill that may run on broad news requests, fetch article content from external sources, and write full reports to disk. The package should be fixed to include its referenced script and template, disclose exactly where reports are stored, and let users choose whether to save reports and what language to use.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description includes very broad trigger phrases such as daily scans, tech news briefings, finance updates, and deep interpretations, which overlap with ordinary user intents and can cause the skill to activate unexpectedly. In a multi-skill environment, this increases the chance of overbroad routing and unintended execution of the skill’s instructions, including network fetching and downstream file-writing behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The response guidelines force all output to be in Simplified Chinese, but the file does not offer the user a language preference or explain a justified locale restriction. This is a natural-language policy issue because it imposes a specific language unconditionally.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill requires always saving full reports to the reports/ directory but provides no user-facing notice, consent step, or retention guidance. Silent persistence can expose sensitive query topics, fetched article content, or user interests on disk, especially in shared or managed environments where local artifacts may be accessible beyond the current session.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.