ClawHub
Back to skill

Security audit

SEO Content Brief Builder

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill performs limited local processing, but its script falls short of the advertised brief generation and its optional Windows app needs separate review.

Expect a basic validation report, not an automatically generated brief. Check headings manually and choose an output folder where replacing seo-content-brief.md is acceptable. The separate unsigned Windows app is unnecessary for this workflow and is not covered by this verdict.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code implements a brief-field validation report, not the advertised content-brief builder. It has no logic for turning a keyword and page goal into content, and its output omits the actual brief fields. Although it performs related length checks, its aggregate H2 check also fails to validate individual heading limits. Local file reads and report writes are ordinary supporting operations; no unrelated or covert capability is evident.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill produces a field-length audit, not the writer-ready content brief promised by its manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises to turn a target keyword and page goal into a writer-ready brief. Instead, run() reads pre-existing title, meta description, slug, and heading fields and writes only their character counts, missing-field notices, and generic guardrails; it neither uses a keyword or page goal nor includes the supplied field contents in the output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.