ClawHub
Back to skill

Security audit

Convert Plaintext to MD

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward markdown-conversion helper with disclosed file-copying and cleanup behavior, and no evidence of hidden execution, persistence, or data theft.

Before installing, users should understand that the skill may create or modify a .md file next to the document they name, and phrases like polishing or finalizing can trigger whole-document formatting cleanup. Review important converted documents afterward if exact whitespace or literal formatting matters.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly states that natural-language variations such as 'polish the converted markdown file' should trigger the 'finalize' behavior. Broad, loosely defined activation phrases can cause unintended mode changes when user instructions are ambiguous, allowing content-modifying cleanup steps to run when the user did not clearly request them. In a document-conversion skill, that increases the risk of accidental content alteration, escaping, reformatting, or structural edits beyond the caller's intent.

Content

No source excerpt is available for this finding.