Back to skill

Security audit

editor

Security checks for vulnerabilities and agentic risk

Overview

This is a text-editing skill with no hidden automation, network access, persistence, or credential use found in the inspected artifacts.

Install this if you want a general-purpose writing cleanup workflow. Review outputs before sending, especially for multilingual text, dialect, sensitive professional messages, or anything where tone and exact wording matter.

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
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
92% confidence
Finding

The description frames the skill as applicable to "anything you write" and "Paste messy text" without defining specific trigger phrases, scope boundaries, or exclusion conditions. In a markdown skill description, this kind of broad activation language can overlap with many ordinary writing-assistance requests and may cause unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill lists 'translated English' as a priority context and later instructs the system to choose a likely context when unclear, which can lead to unsolicited English normalization without explicit user consent. That can alter tone, dialect, or intended linguistic identity, and in sensitive professional or cross-cultural communication it may change meaning or overwrite user preferences.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.