ClawHub
Back to skill

Security audit

Telegram Context

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently provides Telegram chat continuity by reading recent current-chat messages and storing only its own toggle settings.

Before installing, be aware that enabling auto-fetch will add recent messages from the current Telegram chat to the agent context and may send them to your configured LLM provider. Use manual fetch or a low fetch count for sensitive chats, and disable the skill when continuity is not needed.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (1)

Scope Creep

Medium
Confidence
97% confidence
Finding
The manifest's permissions section lists only `message:read` at L011-L012, but the skill documentation describes reading and updating `memory/telegram-context.json` for enablement and timestamps at L033, L040-L043, and L062-L071. This is additional file read/write capability beyond the declared permission baseline.

Static analysis

No suspicious patterns detected.