ClawHub
Back to skill

Security audit

Newsletter SEO Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed newsletter/SEO writing workflow that reads project content, runs local validation scripts, and creates a paste-ready article file without hidden network, credential, persistence, or destructive behavior.

Install only if you want an agent to coordinate a multi-step newsletter/SEO article workflow in your project files. Provide an explicit project slug, keyword, publish date, and article path, and review the generated `-PASTE.md` before publishing manually.

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
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description promises a comprehensive long-form SEO/newsletter production pipeline with multiple substantive stages: SERP analysis, optimized outlining, writing, AI-pattern screening, quality gates, SEO validation, formatting, and publish-doc generation. The supplied code chunk implements only a narrow final-stage utility: building a paste-ready beehiiv document from an already finalized article file, with simple metadata extraction and length warnings. While paste-doc generation and limited SEO metadata validation are consistent with one small part of the description, the actual code does not perform the workflow's primary advertised functions. This is therefore a material description-behavior mismatch.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill instructs the agent to read project files and invoke local scripts, but it does not declare any explicit tool or permission scope. That creates an authorization gap where the agent may access or modify files more broadly than intended, especially because paths are partly derived from runtime inputs like project slugs and article file locations. In a workflow skill that touches the filesystem, missing scope constraints materially increase the chance of unintended file access or overwrite.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger set includes broad phrases like write article and write blog post, which can cause the pipeline to activate in contexts where the user did not intend a filesystem-writing, multi-step automation workflow. Because this skill reads project files, writes output files, and runs scripts, accidental invocation can lead to unintended content generation or modification of project artifacts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The guide requires use of a specific audience vocabulary and prohibits words based on what 'a contractor' would say. This imposes a fixed audience/language style without any opt-in or alternative for other user contexts, which can be a natural-language policy concern under locale/language choice rules.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.