ClawHub
Back to skill

Security audit

copy-editing

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing copy-editing skill with broad but low-impact activation phrases and no executable, persistent, or hidden behavior.

Install this if you want an agent to help edit existing marketing copy. Be aware it may activate on casual editing requests and may read a local product-marketing context file to match brand voice, but the artifact does not add code execution, persistence, or privileged access.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description includes generic activation phrases such as 'proofread,' 'polish this,' 'make this better,' 'update this page,' and 'edit, review, or improve existing marketing copy.' Several of these are common user utterances outside a narrowly defined marketing-copy context, and the description does not provide negative examples or tighter constraints to prevent unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This JSON eval file is a manifest-type file, so vague-trigger checks apply. The expected behavior says the skill "Should trigger on casual phrasing," which is broad and ambiguous because many ordinary user requests could match that wording, and the file provides no explicit constraints or negative examples to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.