ClawHub
Back to skill

Security audit

De Ai Ify

Security checks for vulnerabilities and agentic risk

Overview

This writing helper reads a chosen document and creates a separate humanized output file, with no hidden network, credential, or persistence behavior found.

Before publishing or replacing original content, review the generated '-HUMAN.md' file and change log for meaning changes, factual accuracy, and unwanted tone shifts. Expect the skill to create local output files, but no hidden external access or privileged behavior was found.

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 (2)

Missing User Warnings

Low
Confidence
92% confidence
Finding
The usage section says the skill processes a file and outputs a new `-HUMAN.md` file plus a change log, which is a user-data-affecting behavior. While the output is described, there is no explicit warning or caution about reviewing rewritten content before publishing or about the creation of additional files.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill explicitly states it will create a new "-HUMAN.md" file, which means it performs filesystem writes. While this appears to be part of the intended functionality rather than malicious behavior, the documentation does not clearly warn users up front that running the skill changes local state and creates output files, which can surprise users or cause unintended file proliferation or overwrites depending on implementation.