ClawHub
Back to skill

Security audit

Text In Image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-focused image-generation guide whose external model use is expected and disclosed for its purpose.

Before installing, understand that using this skill may send your prompt text and any provided reference images to external image-generation providers through Runware. Use it when exact visible text matters, and avoid providing sensitive images or private copy unless you are comfortable with that provider flow.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description explicitly says to use this skill even when the user 'just says a poster or a label,' which broadens routing beyond requests that clearly require exact text rendering. In an agent system, this can cause over-selection of the skill for common image-design requests, leading to misrouting, unnecessary tool use, and increased exposure to downstream prompt/tool behaviors when a simpler or more appropriate skill should have been chosen.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.