ClawHub
Back to skill

Security audit

humanizer

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only writing skill is purpose-aligned and disclosed, with the main caution that file mode edits user-selected prose files directly.

Install only if you are comfortable with a writing assistant editing files you point it at. Use version control or review diffs for important drafts, since File mode is intended to modify prose in place.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The markdown explicitly instructs the skill to "Rewrite in place" when the user points at a file, which is a user-data-affecting operation. Although File mode is user-initiated, the description does not include any warning that the skill will modify the target file directly or recommend review/backup before applying changes.

Static analysis

No suspicious patterns detected.