ClawHub
Back to skill

Security audit

markdown-formatting

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown formatting guide with broad activation terms, but it does not ask for hidden access, persistence, network activity, or privileged actions.

Install this if you want agents to apply consistent Markdown wrapping and structure rules. Be aware it may activate during general documentation or style-related work, so review formatting-only changes in sensitive documents before accepting them.

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
Confidence
95% confidence
Finding
The trigger list is broad and includes generic terms like "markdown," "formatting," "documentation," and "style," plus a very expansive natural-language trigger covering writing or editing committed markdown or skill files. This can cause the skill to activate in many unrelated contexts, increasing the chance of unintended behavior, rule collisions with other skills, or over-application of formatting guidance during sensitive edits.

Static analysis

No suspicious patterns detected.