ClawHub
Back to skill

Security audit

Image2Prompt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image-to-prompt guide, but users should be careful with portraits because it asks for demographic and body-description details.

Install only if you are comfortable using it for images you have the right to analyze. For portraits, avoid using it to profile private people or infer sensitive attributes without consent, and prefer non-sensitive visual descriptions when possible.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs extraction and reproduction of sensitive personal appearance attributes from portrait images, including age, ethnicity, skin tone, body type, and attractiveness-framed identity descriptors, without any privacy, consent, or sensitivity safeguards. In an image-analysis skill, this can facilitate profiling, demographic inference, or creation of detailed biometric-style descriptions of real people, making the feature more dangerous than a generic prompt-generation workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.