ClawHub
Back to skill

Security audit

Image Hosting for agents

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward image-hosting API guide, but users should treat uploads as public and understand that quota limits can delete older hosted images.

Install only if you are comfortable giving the agent an AgentImgHost API key and having uploaded images become publicly accessible by direct URL. Avoid uploading screenshots or files containing secrets, personal data, customer data, or sensitive metadata, and consider disabling circular overwrite if older hosted images must not be deleted automatically.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill repeatedly encourages using the returned direct public CDN URL and states uploaded images are immediately accessible worldwide, but it does not prominently warn that uploads are public and may expose sensitive screenshots, documents, or metadata. In an agent context, this increases the risk of accidental disclosure because an automated system may upload user-provided or locally generated images without meaningful consent or privacy review.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Circular Overwrite

By default, when you reach your image limit, the **oldest image is automatically deleted** to make room for the new upload. You can disable this in **Settings** (`https://agent-img.com/config`) to get a `429` error instead.

---
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents that the oldest image is automatically deleted once the quota is reached, but this destructive behavior is presented as a default feature without a strong warning about data loss. For autonomous agents, this can cause unexpected deletion of user assets or evidence, especially if the agent uploads frequently and users assume prior content will remain available.

Static analysis

No suspicious patterns detected.