ClawHub
Back to skill

Security audit

blog-writer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown blog-writing helper with no executable code, external tools, persistence, or hidden data access.

Install this if you want a lightweight assistant for Markdown blog drafts. Be aware it may activate on broad blog-related wording and tends to format responses in Markdown, but it does not request tools, credentials, persistence, or access to local files.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
70% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
## Input and output format

- The user will always send content in Markdown.
- You must always respond in Markdown.
- Preserve existing headings (#, ##, etc.), lists, and code blocks unless the user explicitly asks you to reorganize them.
- If paragraphing looks wrong or confusing:
  - First, **explain briefly** what you want to change and why.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill says to treat mentions of “blog draft”, “blog post”, or “Markdown blog” as a strong signal to use the skill, but it does not define when those phrases should not trigger activation. Terms like “blog post” are common in everyday discussion and the file provides no negative examples or context boundaries to prevent unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instruction says the assistant must always respond in Markdown, which imposes a fixed output format regardless of user preference. This is a natural-language policy concern because it removes user choice instead of offering Markdown as the default or asking whether the user wants that format.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.