ClawHub
Back to skill

Security audit

content-writer-images

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small visual-briefing helper that requires user approval before any remote image request and does not include executable code.

Before installing, note that using this skill with a remote image provider can send the approved prompt and related section text to that provider. The artifact directs the agent to show those details first and wait for your confirmation.

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)

Autonomous Decision Making

Medium
Category
Excessive Agency
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.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
## Permission gate

Before any remote image request, show and obtain approval for the provider, exact prompt, text that would be transmitted, section, image count, aspect ratio, and output location. Never ask users to paste secrets into chat.

## Workflow

Static analysis

No suspicious patterns detected.