ClawHub
Back to skill

Security audit

Automated Content Machine

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small content-automation prompt, but it directs agents toward automatic public posting without clear approval or account-safety boundaries.

Review this skill carefully before installing if the agent has access to real social, blog, newsletter, or commerce accounts. Configure any integrations to create drafts or scheduled items for review, and require explicit approval before publishing or modifying live accounts.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly promises fully automated content generation and publishing across external platforms, but it provides no warning about account-impacting actions, credential use, privacy exposure, or the need for explicit user confirmation before posting. In an agent setting, this can lead to unintended publication, disclosure of sensitive material, reputational harm, or unauthorized actions on connected accounts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states that blog posts are automatically published to WordPress/Ghost, which are external sites that can be modified through authenticated actions, yet it omits any warning or control boundary around those changes. This is dangerous because an agent could publish incorrect, sensitive, or policy-violating content directly to production sites without clear consent or review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The manifest description and introductory text are presented in Chinese, and the file does not indicate that users may choose another language or locale. This can be a language/locale policy concern when a skill appears to enforce a language without explicit opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.