ClawHub
Back to skill

Security audit

PLS Copy Editing

Security checks for vulnerabilities and agentic risk

Overview

This appears to be an unfinished copy-editing skill template with unclear instructions, but it does not contain code, persistence, credential handling, data exfiltration, or other high-impact behavior.

Do not rely on this skill as published because it is unfinished and may be invoked inconsistently. It should be completed with a clear copy-editing purpose, concrete triggers, exclusions, and editing boundaries before installation, but the current artifact does not show malicious behavior.

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
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill's metadata and operating guidance are left as TODO placeholders, so an agent cannot reliably determine when this skill should or should not be invoked. Ambiguous invocation criteria can cause the skill to be applied in inappropriate contexts, leading to incorrect edits, workflow misuse, or accidental handling of content outside its intended scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.