Back to skill

Security audit

refine-markdown-to-mkdocs

Security checks for vulnerabilities and agentic risk

Overview

This skill is a note-refinement formatter that reads a user-selected markdown file and creates related markdown outputs without hidden execution, networking, credential access, or persistence.

Before installing, understand that the skill may rewrite, merge, and omit material in its generated refined copy. Use it on intended note files, review the plan before approval, and check where the plan, refined output, and backup files will be created.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description includes broad invocation phrases like 'clean up notes', 'summarize reading', and 'refine bookmarks', which can cause the skill to trigger in situations beyond the user's precise intent. Overbroad routing increases the chance that unreviewed content transformation or file-modifying behavior is applied to sensitive or unintended inputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to save output files and back up existing refined files, but it does not require a clear user-facing warning or explicit consent before modifying the filesystem. In an agent setting, silent writes and backups can overwrite user expectations, create unwanted artifacts, or modify the wrong file when the target is inferred incorrectly.

Content

No source excerpt is available for this finding.