ClawHub
Back to skill

Security audit

Tech Blog Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local blog-post template generator with some overstated or broken features, but no evidence of malicious or high-impact behavior.

Install only if you are comfortable with a basic local Markdown template generator. Treat the advertised advanced features as unreliable until fixed, and avoid passing confidential article ideas or internal descriptions if terminal output may be logged or shared.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared purpose is only partially accurate. The script does produce Markdown output and includes code blocks, so those aspects align. However, its primary behavior is a static template generator rather than a tool that generates professional technical blog posts from simple outlines. It never parses or expands an outline into content, and there is no real SEO optimization logic such as metadata generation, keyword handling, internal linking, or structured formatting beyond a printed slug. Additionally, the tags line in the main output is populated before the variable is assigned, so tag support is not functioning as described. Therefore, the description materially overstates the capability of the code.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

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.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest says the skill supports Markdown generation with tags, and the usage comment advertises an optional --tags argument. However, the here-document prints $TAGS_TAG_LINE at L046 before the variable is populated later at L172-L177, so provided tags never actually appear in the generated post.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This code file produces a full blog post template by interpolating user-supplied TITLE and DESCRIPTION into output, which could expose draft or internal content if run in a shared terminal or captured logs. There is no user-facing warning in comments, usage text, or output messaging about this disclosure behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.