ClawHub
Back to skill

Security audit

News Telegram Push

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only news curation skill with strict formatting rules and no artifact-backed signs of hidden execution, persistence, credential access, or data exfiltration.

Installers should understand that this skill is designed for English-only, link-only news pushes and suppresses summaries and visible source labels. If connected to an actual Telegram sender or scheduler, keep user review and posting controls outside the skill, since the artifact itself does not implement those safeguards.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The markdown explicitly requires output in English only. This is a natural-language locale restriction, and the file does not offer the user a language choice or explain why English-only output is necessary for a region-specific or compliance-bound use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The final rule again mandates English-only output. Reiterating the restriction confirms that the skill is designed to force a single language rather than offering localization or user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.