ClawHub
Back to skill

Security audit

News Curator

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed scheduled news-curation skill that sends public news briefings to Telegram, with recurring delivery clearly part of its stated purpose.

Before installing, confirm the Telegram destination and schedule are what you want, and avoid adding prompts or sources that could place sensitive information into the briefing because messages are sent externally on a recurring schedule.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly states that the agent's response is automatically delivered to Telegram, but it provides no user-facing disclosure, confirmation step, or indication that curated content will be transmitted to an external service. This creates a privacy and consent risk because fetched content, summaries, links, or accidentally included sensitive data could be sent outside the local agent environment without the user's explicit awareness at send time.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.