ClawHub
Back to skill

Security audit

Error Prone

Security checks for vulnerabilities and agentic risk

Overview

This skill only edits text, but it is explicitly designed to make AI-written content look like it was written by a person, which raises authenticity and disclosure concerns.

Review this carefully before installing. It has no code execution or credential access, but it can make AI-written text appear intentionally less detectable as AI-written. Use it only for transparent stylistic editing, not where recipients, platforms, schools, employers, or disclosure rules expect AI involvement to be identified.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad and overlap with ordinary writing/editing requests such as 'make it sound human' or 'humanize this,' which can cause the skill to activate in contexts the user did not explicitly intend. In this specific skill, unintended activation is more dangerous because the skill is designed to make AI output appear less detectable as AI-written, potentially bypassing transparency or policy expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly aims to make AI-generated text seem non-AI-generated, but the description does not warn about deception, misuse, or policy-sensitive contexts. That omission materially increases risk because users or orchestration systems may treat it as a harmless tone-editing tool when it is actually an evasion-oriented capability intended to reduce AI detectability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.