ClawHub
Back to skill

Security audit

News Aggregator Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed news-aggregation workflow with expected web fetching and local report output, with some usage caveats but no artifact-backed malicious behavior.

Before installing, expect the skill to make outbound requests to news and social sources, optionally extract full article text in deep mode, and save generated reports locally under reports/. Avoid using it for sensitive research topics on shared machines unless local report retention is acceptable.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The --deep mode explicitly downloads and extracts full article text from external sites, but the skill does not disclose this network retrieval or the scope of content collection to the user. This can trigger unexpected outbound requests, increased exposure to untrusted content, and collection of larger bodies of third-party text than the user may realize, which is especially relevant in security-sensitive or privacy-constrained environments.

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 explicitly require the output language to be Simplified Chinese. Because this is a blanket language requirement with no user opt-in or explanation of a region-specific constraint, it violates the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill requires always saving a full report to the local reports/ directory but does not warn the user that content will be persisted to disk. This creates an unexpected data-retention side effect: fetched article content, user-request context, or derived analysis may be stored locally without consent, which can expose sensitive interests, prompts, or copyrighted material to other users or processes on the system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.