ClawHub
Back to skill

Security audit

SEO Content Writer (Hybrid Labs)

Security checks for vulnerabilities and agentic risk

Overview

This SEO writing skill is coherent and low risk, though its generic trigger phrases may make it activate for ordinary writing requests.

Install with normal caution for a writing assistant: expect it to steer general article requests toward SEO structure, and only connect SEO tools or Search Console data if you are comfortable using those site metrics for content drafting.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list includes broad phrases like `content writing`, `write an article`, and `blog writing`, which can match many ordinary user requests outside SEO-specific intent. Over-broad invocation can cause the wrong skill to activate, pulling in extra instructions and reference-reading behavior unexpectedly, which increases the chance of prompt-routing mistakes and unintended context exposure.

Static analysis

No suspicious patterns detected.