ClawHub
Back to skill

Security audit

TG Image Sender

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Telegram image-sending helper, but its broad trigger phrases and silent post-send behavior could cause unintended external sharing.

Review before installing. Use this only if you want the agent to send images to Telegram, and prefer adding explicit confirmation and destination checks before any user-provided image, file path, or URL is transmitted.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description contains broad trigger phrases such as 'send photo' and 'show image in Telegram', which can overlap with ordinary user requests and cause the skill to activate when the user did not clearly intend external delivery to Telegram. In this context, overbroad matching is risky because the action sends media to an external channel, potentially causing unintended disclosure or message delivery.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to send media to Telegram and then suppress a follow-up response with 'NO_REPLY', but it does not warn about privacy, third-party transmission, or the fact that user-provided images/URLs will be sent to an external service. This reduces user awareness and can lead to accidental sharing of sensitive content outside the current environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.